• About TC
  • Affiliate Disclaimer
  • Privacy Policy
  • TOS
  • Contact
Thursday, July 3, 2025
Techcratic
  • TC
  • AI
    Artificial Intelligence

    EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video

    Artificial Intelligence

    Instruction-Following Pruning for Large Language Models

    Artificial Intelligence

    How to Combine Streamlit, Pandas, and Plotly for Interactive Data Apps

    Artificial Intelligence

    Tailor responsible AI with new safeguard tiers in Amazon Bedrock Guardrails

    Artificial Intelligence

    Automate Data Quality Reports with n8n: From CSV to Professional Analysis

    Artificial Intelligence

    NewDay builds A Generative AI based Customer service Agent Assist with over 90% accuracy

    Artificial Intelligence

    5 Things You Need to Know About Agentic AI

    Artificial Intelligence

    Normalizing Flows are Capable Generative Models

    Artificial Intelligence

    Update on the AWS DeepRacer Student Portal

  • App Zone
    Top 3 Launcher Apps for Apple: Features, Pros, and Cons

    Top 3 Launcher Apps for Apple: Features, Pros, and Cons

    Top 3 Launcher Apps for Android: Features, Pros, and Cons

    Top 3 Launcher Apps for Android: Features, Pros, and Cons

    Top 3 Card Game Apps of 2025: Features, Pros, and Cons

    Top 3 Card Game Apps of 2025: Features, Pros, and Cons

    Top 3 Medical Apps of 2025: Features, Pros, and Cons

    Top 3 Medical Apps of 2025: Features, Pros, and Cons

    Top 3 Travel Apps of 2025: Features, Pros, and Cons

    Top 3 Travel Apps of 2025: Features, Pros, and Cons

    Top 3 Casual Game Apps for 2025: Features, Pros, and Cons

    Top 3 Casual Game Apps for 2025: Features, Pros, and Cons

    Top 3 Food Apps for 2025: Features, Pros, and Cons

    Top 3 Food Apps for 2025: Features, Pros, and Cons

    Top 3 Sport Apps for 2025: Features, Pros, and Cons

    Top 3 Sport Apps for 2025: Features, Pros, and Cons

    Top 3 Productivity Apps for 2025: Features, Pros, and Cons

    Top 3 Productivity Apps for 2025: Features, Pros, and Cons

  • Apple
    M4 iPad Pro, iPad A16, Apple Pencil Pro, AirTag, more 9to5Mac

    M4 iPad Pro, iPad A16, Apple Pencil Pro, AirTag, more 9to5Mac

    iPhone expansion, Foxconn India drops Chinese experts, mystery

    Qantas data breach exposes personal details of millions

    Qantas data breach exposes personal details of millions

    July 2, 2025 – iPhone Fold, Apple vs DOJ

    Five new Apple products are launching early this year, here’s what’s coming

    Apple is launching 15+ new products this fall, here’s what’s coming

    iOS 26’s new Liquid Glass design looks like a major win for Apple

    iOS 26’s new Liquid Glass design looks like a major win for Apple

    OLED MacBook Pro still expected for 2026 release

    OLED MacBook Pro still expected for 2026 release

    Trump Vietnam deal, costs, AirPods, iPad, Apple Watch, Mac mini

    Trump Vietnam deal, costs, AirPods, iPad, Apple Watch, Mac mini

    iPadOS 26 is perfect for the larger iPad model that’s coming

    Apple’s ‘iPad Fold’ won’t be launching any time soon, per new report

  • Retro Rewind
    Retro Rewind: Electronic Games April 1995

    Retro Rewind: Electronic Games April 1995

    Retro Rewind: Electronic Gaming Monthly Magazine Number 55 February 1994

    Retro Rewind: Electronic Gaming Monthly Magazine Number 57 April 1994

    Retro Rewind: Blast from the Past – 35 Iconic Commercials of 1988!

    Retro Rewind: Blast from the Past – 35 Iconic Commercials of 1988!

    Retro Rewind: PC World Magazine August 1998

    Retro Rewind: PC World Magazine August 1998

    Retro Rewind: Computer Shopper Magazine September 1997

    Retro Rewind: Computer Shopper Magazine September 1997

    Retro Rewind: PC Magazine December 2015

    Retro Rewind: PC Magazine December 2015

    Retro Rewind: EDGE Magazine RETRO #1: The Guide to Classic Videogame Playing and Collecting

    Retro Rewind: EDGE Magazine RETRO #1: The Guide to Classic Videogame Playing and Collecting

    Retro Rewind: Computer Gaming World Magazine Issue 73 December 1998

    Retro Rewind: Computer Gaming World Magazine Issue 73 December 1998

    Retro Rewind: Electronic Gaming Monthly Magazine Number 55 February 1994

    Retro Rewind: Electronic Gaming Monthly Magazine Number 55 February 1994

  • Tech Deals
    SanDisk 128GB Extreme PRO SDXC UHS-I Memory Card – C10, U3, V30, 4K UHD, SD Card -…

    SanDisk 128GB Extreme PRO SDXC UHS-I Memory Card – C10, U3, V30, 4K UHD, SD Card -…

    Vantec USB 3.0 Multi-Card Reader UHS-II, SD 4.0, Multi-LUN (UGT-CR615), Black

    Vantec USB 3.0 Multi-Card Reader UHS-II, SD 4.0, Multi-LUN (UGT-CR615), Black

    TAGRY Bluetooth Headphones True Wireless Earbuds 60H Playback LED Power Display…

    TAGRY Bluetooth Headphones True Wireless Earbuds 60H Playback LED Power Display…

    SABRENT 13 Port High Speed USB 2.0 Hub with Power Adapter and 2 Control Switches…

    SABRENT 13 Port High Speed USB 2.0 Hub with Power Adapter and 2 Control Switches…

    ORICO MiniTower 2 Bay RAID Enclosure Compatible NVMe SSD 10Gbps with Expansion Hub…

    ORICO MiniTower 2 Bay RAID Enclosure Compatible NVMe SSD 10Gbps with Expansion Hub…

    Blue Yeti USB Mic for Recording and Streaming on PC and Mac with Blue VOCE Effects, 4…

    Blue Yeti USB Mic for Recording and Streaming on PC and Mac with Blue VOCE Effects, 4…

    Lenovo V15 Laptop | 15.6″ FHD Anti-Glare Display | AMD Ryzen 7 7730U | 40GB RAM | 1TB…

    Lenovo V15 Laptop | 15.6″ FHD Anti-Glare Display | AMD Ryzen 7 7730U | 40GB RAM | 1TB…

    SABRENT 1TB Rocket Nano XTRM External SSD, USB 3.2 / Thunderbolt 3, Speeds Up to…

    SABRENT 1TB Rocket Nano XTRM External SSD, USB 3.2 / Thunderbolt 3, Speeds Up to…

    MIXAGE 64GB CompactFlash Card UDMA7, 120MB/s Read 45MB/s Write, 85TB TBW, for Canon…

    MIXAGE 64GB CompactFlash Card UDMA7, 120MB/s Read 45MB/s Write, 85TB TBW, for Canon…

  • Tech Eats
    Cheesy Broccoli Rice Mug: 5-Minute Super Comfort Food

    Cheesy Broccoli Rice Mug: 5-Minute Super Comfort Food

    Top 10 Vegetarian Recipes for 2025: Easy and Nutritious Meals for Busy People

    Top 10 Vegetarian Recipes for 2025: Easy and Nutritious Meals for Busy People

    Bacon Mug Lasagna: 5-Minute Microwave Meat Lover’s Dream

    Bacon Mug Lasagna: 5-Minute Microwave Meat Lover’s Dream

    Bacon Fried Rice Mug: 5-Minute Microwave Meal

    Bacon Fried Rice Mug: 5-Minute Microwave Meal

    Bacon & Cheddar Mug Biscuit: 2-Minute Savory Comfort

    Bacon & Cheddar Mug Biscuit: 2-Minute Savory Comfort

    Loaded Bacon Cheesy Potato Mug: 5-Minute Comfort Food

    Loaded Bacon Cheesy Potato Mug: 5-Minute Comfort Food

    Peanut Butter Banana Mug Muffin: 5-Minute Protein Snack

    Peanut Butter Banana Mug Muffin: 5-Minute Protein Snack

    Oreo Mug Cake: 2-Minute Cookie & Cake Combo!

    Oreo Mug Cake: 2-Minute Cookie & Cake Combo!

    Tiramisu Mug Cake: Coffee Lover’s Dream in 2 Minutes!

    Tiramisu Mug Cake: Coffee Lover’s Dream in 2 Minutes!

  • Tesla
    Center Console Cover for Tesla Model 3 Model Y Leather Armrest Box Cushion Protector…

    Center Console Cover for Tesla Model 3 Model Y Leather Armrest Box Cushion Protector…

    Femuar Car Trunk Organizer with Large Capacity Waterproof Car Accessories for Women &…

    Femuar Car Trunk Organizer with Large Capacity Waterproof Car Accessories for Women &…

    [Replacement] 4Pcs Roof Rack Cover Cap Rail End Shell for Tesla for Model 3 2017 2018…

    [Replacement] 4Pcs Roof Rack Cover Cap Rail End Shell for Tesla for Model 3 2017 2018…

    Lower Center Console Organizer Tray for Tesla Model Y 2021-2024 & Model 3 2021-2023,…

    Lower Center Console Organizer Tray for Tesla Model Y 2021-2024 & Model 3 2021-2023,…

    Tesla unveils new cheaper, but nerfed ‘Long Range’ Cybertruck

    Tesla confirms Cybertruck sales are down to just ~5,000 units

    OEDRO Floor Mats Fit for Tesla Model 3 Highland 2024 2025, All Weather Waterproof…

    OEDRO Floor Mats Fit for Tesla Model 3 Highland 2024 2025, All Weather Waterproof…

    Tesla (TSLA) confirms 384,000 deliveries in Q2 2025, right on expectations

    Tesla (TSLA) confirms 384,000 deliveries in Q2 2025, right on expectations

    2025 Upgraded NACS to CCS Adapter, 500A/1000V, 250 kW DC Fast Charging for Ford, Rivian,…

    2025 Upgraded NACS to CCS Adapter, 500A/1000V, 250 kW DC Fast Charging for Ford, Rivian,…

    for Tesla Model 3 Floor mat, 3D Custom car mat for Model 3 2017-2025, All Weather Floor…

    for Tesla Model 3 Floor mat, 3D Custom car mat for Model 3 2017-2025, All Weather Floor…

  • UFO
    Pegasus Hobbies PEG9119 Model Kit, Multi, Standard Size

    Pegasus Hobbies PEG9119 Model Kit, Multi, Standard Size

    The Venus Mission That Shocked Soviet Scientists  – Space Exploration Missions

    The Venus Mission That Shocked Soviet Scientists – Space Exploration Missions

    Unidentified

    Unidentified

    Paranormal Activity: The Ghost Dimension | official trailer (2015)

    Paranormal Activity: The Ghost Dimension | official trailer (2015)

    Interstellar Secrets of Ancient Civilizations | Ancient Aliens

    Interstellar Secrets of Ancient Civilizations | Ancient Aliens

    UFO Shape LED Dual Purpose Lamp, Portable Adjustable Light Color and Brightness Outdoor Lamp, Motion Sensor Night Lamp, Magnetic Fixation, Rechargeable Flying Saucer Shape Lamp (White)

    UFO Shape LED Dual Purpose Lamp, Portable Adjustable Light Color and Brightness Outdoor Lamp, Motion Sensor Night Lamp, Magnetic Fixation, Rechargeable Flying Saucer Shape Lamp (White)

    UFO – Unidentified Flying Object (Drum Cover)

    UFO – Unidentified Flying Object (Drum Cover)

    Mademark x MTV – Cryptid MTV Logo Featuring Bigfoot, UFO, Aliens & Nessie T-Shirt

    Mademark x MTV – Cryptid MTV Logo Featuring Bigfoot, UFO, Aliens & Nessie T-Shirt

    Area 51 Security Costume T-Shirt

    Area 51 Security Costume T-Shirt

No Result
View All Result
  • TC
  • AI
    Artificial Intelligence

    EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video

    Artificial Intelligence

    Instruction-Following Pruning for Large Language Models

    Artificial Intelligence

    How to Combine Streamlit, Pandas, and Plotly for Interactive Data Apps

    Artificial Intelligence

    Tailor responsible AI with new safeguard tiers in Amazon Bedrock Guardrails

    Artificial Intelligence

    Automate Data Quality Reports with n8n: From CSV to Professional Analysis

    Artificial Intelligence

    NewDay builds A Generative AI based Customer service Agent Assist with over 90% accuracy

    Artificial Intelligence

    5 Things You Need to Know About Agentic AI

    Artificial Intelligence

    Normalizing Flows are Capable Generative Models

    Artificial Intelligence

    Update on the AWS DeepRacer Student Portal

  • App Zone
    Top 3 Launcher Apps for Apple: Features, Pros, and Cons

    Top 3 Launcher Apps for Apple: Features, Pros, and Cons

    Top 3 Launcher Apps for Android: Features, Pros, and Cons

    Top 3 Launcher Apps for Android: Features, Pros, and Cons

    Top 3 Card Game Apps of 2025: Features, Pros, and Cons

    Top 3 Card Game Apps of 2025: Features, Pros, and Cons

    Top 3 Medical Apps of 2025: Features, Pros, and Cons

    Top 3 Medical Apps of 2025: Features, Pros, and Cons

    Top 3 Travel Apps of 2025: Features, Pros, and Cons

    Top 3 Travel Apps of 2025: Features, Pros, and Cons

    Top 3 Casual Game Apps for 2025: Features, Pros, and Cons

    Top 3 Casual Game Apps for 2025: Features, Pros, and Cons

    Top 3 Food Apps for 2025: Features, Pros, and Cons

    Top 3 Food Apps for 2025: Features, Pros, and Cons

    Top 3 Sport Apps for 2025: Features, Pros, and Cons

    Top 3 Sport Apps for 2025: Features, Pros, and Cons

    Top 3 Productivity Apps for 2025: Features, Pros, and Cons

    Top 3 Productivity Apps for 2025: Features, Pros, and Cons

  • Apple
    M4 iPad Pro, iPad A16, Apple Pencil Pro, AirTag, more 9to5Mac

    M4 iPad Pro, iPad A16, Apple Pencil Pro, AirTag, more 9to5Mac

    iPhone expansion, Foxconn India drops Chinese experts, mystery

    Qantas data breach exposes personal details of millions

    Qantas data breach exposes personal details of millions

    July 2, 2025 – iPhone Fold, Apple vs DOJ

    Five new Apple products are launching early this year, here’s what’s coming

    Apple is launching 15+ new products this fall, here’s what’s coming

    iOS 26’s new Liquid Glass design looks like a major win for Apple

    iOS 26’s new Liquid Glass design looks like a major win for Apple

    OLED MacBook Pro still expected for 2026 release

    OLED MacBook Pro still expected for 2026 release

    Trump Vietnam deal, costs, AirPods, iPad, Apple Watch, Mac mini

    Trump Vietnam deal, costs, AirPods, iPad, Apple Watch, Mac mini

    iPadOS 26 is perfect for the larger iPad model that’s coming

    Apple’s ‘iPad Fold’ won’t be launching any time soon, per new report

  • Retro Rewind
    Retro Rewind: Electronic Games April 1995

    Retro Rewind: Electronic Games April 1995

    Retro Rewind: Electronic Gaming Monthly Magazine Number 55 February 1994

    Retro Rewind: Electronic Gaming Monthly Magazine Number 57 April 1994

    Retro Rewind: Blast from the Past – 35 Iconic Commercials of 1988!

    Retro Rewind: Blast from the Past – 35 Iconic Commercials of 1988!

    Retro Rewind: PC World Magazine August 1998

    Retro Rewind: PC World Magazine August 1998

    Retro Rewind: Computer Shopper Magazine September 1997

    Retro Rewind: Computer Shopper Magazine September 1997

    Retro Rewind: PC Magazine December 2015

    Retro Rewind: PC Magazine December 2015

    Retro Rewind: EDGE Magazine RETRO #1: The Guide to Classic Videogame Playing and Collecting

    Retro Rewind: EDGE Magazine RETRO #1: The Guide to Classic Videogame Playing and Collecting

    Retro Rewind: Computer Gaming World Magazine Issue 73 December 1998

    Retro Rewind: Computer Gaming World Magazine Issue 73 December 1998

    Retro Rewind: Electronic Gaming Monthly Magazine Number 55 February 1994

    Retro Rewind: Electronic Gaming Monthly Magazine Number 55 February 1994

  • Tech Deals
    SanDisk 128GB Extreme PRO SDXC UHS-I Memory Card – C10, U3, V30, 4K UHD, SD Card -…

    SanDisk 128GB Extreme PRO SDXC UHS-I Memory Card – C10, U3, V30, 4K UHD, SD Card -…

    Vantec USB 3.0 Multi-Card Reader UHS-II, SD 4.0, Multi-LUN (UGT-CR615), Black

    Vantec USB 3.0 Multi-Card Reader UHS-II, SD 4.0, Multi-LUN (UGT-CR615), Black

    TAGRY Bluetooth Headphones True Wireless Earbuds 60H Playback LED Power Display…

    TAGRY Bluetooth Headphones True Wireless Earbuds 60H Playback LED Power Display…

    SABRENT 13 Port High Speed USB 2.0 Hub with Power Adapter and 2 Control Switches…

    SABRENT 13 Port High Speed USB 2.0 Hub with Power Adapter and 2 Control Switches…

    ORICO MiniTower 2 Bay RAID Enclosure Compatible NVMe SSD 10Gbps with Expansion Hub…

    ORICO MiniTower 2 Bay RAID Enclosure Compatible NVMe SSD 10Gbps with Expansion Hub…

    Blue Yeti USB Mic for Recording and Streaming on PC and Mac with Blue VOCE Effects, 4…

    Blue Yeti USB Mic for Recording and Streaming on PC and Mac with Blue VOCE Effects, 4…

    Lenovo V15 Laptop | 15.6″ FHD Anti-Glare Display | AMD Ryzen 7 7730U | 40GB RAM | 1TB…

    Lenovo V15 Laptop | 15.6″ FHD Anti-Glare Display | AMD Ryzen 7 7730U | 40GB RAM | 1TB…

    SABRENT 1TB Rocket Nano XTRM External SSD, USB 3.2 / Thunderbolt 3, Speeds Up to…

    SABRENT 1TB Rocket Nano XTRM External SSD, USB 3.2 / Thunderbolt 3, Speeds Up to…

    MIXAGE 64GB CompactFlash Card UDMA7, 120MB/s Read 45MB/s Write, 85TB TBW, for Canon…

    MIXAGE 64GB CompactFlash Card UDMA7, 120MB/s Read 45MB/s Write, 85TB TBW, for Canon…

  • Tech Eats
    Cheesy Broccoli Rice Mug: 5-Minute Super Comfort Food

    Cheesy Broccoli Rice Mug: 5-Minute Super Comfort Food

    Top 10 Vegetarian Recipes for 2025: Easy and Nutritious Meals for Busy People

    Top 10 Vegetarian Recipes for 2025: Easy and Nutritious Meals for Busy People

    Bacon Mug Lasagna: 5-Minute Microwave Meat Lover’s Dream

    Bacon Mug Lasagna: 5-Minute Microwave Meat Lover’s Dream

    Bacon Fried Rice Mug: 5-Minute Microwave Meal

    Bacon Fried Rice Mug: 5-Minute Microwave Meal

    Bacon & Cheddar Mug Biscuit: 2-Minute Savory Comfort

    Bacon & Cheddar Mug Biscuit: 2-Minute Savory Comfort

    Loaded Bacon Cheesy Potato Mug: 5-Minute Comfort Food

    Loaded Bacon Cheesy Potato Mug: 5-Minute Comfort Food

    Peanut Butter Banana Mug Muffin: 5-Minute Protein Snack

    Peanut Butter Banana Mug Muffin: 5-Minute Protein Snack

    Oreo Mug Cake: 2-Minute Cookie & Cake Combo!

    Oreo Mug Cake: 2-Minute Cookie & Cake Combo!

    Tiramisu Mug Cake: Coffee Lover’s Dream in 2 Minutes!

    Tiramisu Mug Cake: Coffee Lover’s Dream in 2 Minutes!

  • Tesla
    Center Console Cover for Tesla Model 3 Model Y Leather Armrest Box Cushion Protector…

    Center Console Cover for Tesla Model 3 Model Y Leather Armrest Box Cushion Protector…

    Femuar Car Trunk Organizer with Large Capacity Waterproof Car Accessories for Women &…

    Femuar Car Trunk Organizer with Large Capacity Waterproof Car Accessories for Women &…

    [Replacement] 4Pcs Roof Rack Cover Cap Rail End Shell for Tesla for Model 3 2017 2018…

    [Replacement] 4Pcs Roof Rack Cover Cap Rail End Shell for Tesla for Model 3 2017 2018…

    Lower Center Console Organizer Tray for Tesla Model Y 2021-2024 & Model 3 2021-2023,…

    Lower Center Console Organizer Tray for Tesla Model Y 2021-2024 & Model 3 2021-2023,…

    Tesla unveils new cheaper, but nerfed ‘Long Range’ Cybertruck

    Tesla confirms Cybertruck sales are down to just ~5,000 units

    OEDRO Floor Mats Fit for Tesla Model 3 Highland 2024 2025, All Weather Waterproof…

    OEDRO Floor Mats Fit for Tesla Model 3 Highland 2024 2025, All Weather Waterproof…

    Tesla (TSLA) confirms 384,000 deliveries in Q2 2025, right on expectations

    Tesla (TSLA) confirms 384,000 deliveries in Q2 2025, right on expectations

    2025 Upgraded NACS to CCS Adapter, 500A/1000V, 250 kW DC Fast Charging for Ford, Rivian,…

    2025 Upgraded NACS to CCS Adapter, 500A/1000V, 250 kW DC Fast Charging for Ford, Rivian,…

    for Tesla Model 3 Floor mat, 3D Custom car mat for Model 3 2017-2025, All Weather Floor…

    for Tesla Model 3 Floor mat, 3D Custom car mat for Model 3 2017-2025, All Weather Floor…

  • UFO
    Pegasus Hobbies PEG9119 Model Kit, Multi, Standard Size

    Pegasus Hobbies PEG9119 Model Kit, Multi, Standard Size

    The Venus Mission That Shocked Soviet Scientists  – Space Exploration Missions

    The Venus Mission That Shocked Soviet Scientists – Space Exploration Missions

    Unidentified

    Unidentified

    Paranormal Activity: The Ghost Dimension | official trailer (2015)

    Paranormal Activity: The Ghost Dimension | official trailer (2015)

    Interstellar Secrets of Ancient Civilizations | Ancient Aliens

    Interstellar Secrets of Ancient Civilizations | Ancient Aliens

    UFO Shape LED Dual Purpose Lamp, Portable Adjustable Light Color and Brightness Outdoor Lamp, Motion Sensor Night Lamp, Magnetic Fixation, Rechargeable Flying Saucer Shape Lamp (White)

    UFO Shape LED Dual Purpose Lamp, Portable Adjustable Light Color and Brightness Outdoor Lamp, Motion Sensor Night Lamp, Magnetic Fixation, Rechargeable Flying Saucer Shape Lamp (White)

    UFO – Unidentified Flying Object (Drum Cover)

    UFO – Unidentified Flying Object (Drum Cover)

    Mademark x MTV – Cryptid MTV Logo Featuring Bigfoot, UFO, Aliens & Nessie T-Shirt

    Mademark x MTV – Cryptid MTV Logo Featuring Bigfoot, UFO, Aliens & Nessie T-Shirt

    Area 51 Security Costume T-Shirt

    Area 51 Security Costume T-Shirt

No Result
View All Result
Techcratic
No Result
View All Result
Home Hacker News

Stop Building AI Agents: Use Smarter LLM Workflows

Hacker News by Hacker News
July 2, 2025
in Hacker News
Reading Time: 22 mins read
129
A A
0

2025-07-02 20:02:00
decodingml.substack.com

Paul: Today, the scene is owned by Hugo, a brilliant mind who advises and teaches teams building LLM-powered systems, including engineers from Netflix, Meta, and the U.S. Air Force.

He runs a course on the LLM software development lifecycle, focusing on everything from retrieval and evaluation to agent design, and all the intermediate steps in between.

Enough talking, I’ll let him dig into today’s controversial topic: “Stop building AI agents”. ↓🎙️

P.S. I agree with him. 🤫

Hugo: I’ve taught and advised dozens of teams building LLM-powered systems. There’s a common pattern I keep seeing, and honestly, it’s frustrating.

Everyone reaches for agents first. They set up memory systems. They add routing logic. They create tool definitions and character backstories. It feels powerful and it feels like progress.

Until everything breaks. And when things go wrong (which they always do), nobody can figure out why.

Was it the agent forgetting its task? Is the wrong tool getting selected? Too many moving parts to debug? Is the whole system fundamentally brittle?

I learned this the hard way. Six months ago, I built a “research crew” with CrewAI: three agents, five tools, perfect coordination on paper. But in practice? The researcher ignored the web scraper, the summarizer forgot to use the citation tool And the coordinator gave up entirely when processing longer documents. It was a beautiful plan falling apart in spectacular ways.

This flowchart came from one of my lessons after debugging countless broken agent systems. Notice that tiny box at the end? That’s how rarely you actually need agents. Yet everyone starts there.

This post is about what I learned from those failures, including how to avoid them entirely.

The patterns I’ll walk through are inspired by Anthropic’s Building Effective Agents post. But these aren’t theory. This is real code, real failures, and real decisions I’ve made while teaching these systems. Every example here comes from actual projects I’ve built or debugged.

You’ll discover why agents aren’t the answer (most of the time). And more importantly, you’ll learn what to build instead.

What You’ll Learn:

  • Why agents are usually not the right first step

  • Five LLM workflow patterns that solve most problems

  • When agents are the right tool and how to build them safely

🔗 All examples come from this GitHub notebook

Everyone thinks agents are where you start. It’s not their fault: frameworks make it seem easy, demo videos are exciting, and tech Twitter loves the hype.

But here’s what I learned after building that CrewAI research crew: most agent systems break down from too much complexity, not too little.

In my demo, I had three agents working together:

  • A researcher agent that could browse web pages

  • A summarizer agent with access to citation tools

  • A coordinator agent that managed task delegation

Pretty standard stuff, right? Except in practice:

  • The researcher ignored the web scraper 70% of the time

  • The summarizer completely forgot to use citations when processing long documents

  • The coordinator threw up its hands when tasks weren’t clearly defined

So wait: “What exactly is an agent?” To answer that, we need to look at 4 characteristics of LLM systems.

  1. Memory: Let the LLM remember past interactions

  2. Information Retrieval: Add RAG for context

  3. Tool Usage: Give the LLM access to functions and APIs

  4. Workflow Control: The LLM output controls which tools are used and when
    ^ This makes an agent

When people say “agent,” they mean that last step: the LLM output controls the workflow. Most people skip straight to letting the LLM control the workflow without realizing that simpler patterns often work better. Using an agent means handing control to the LLM. But unless your task is so dynamic that its flow can’t be defined upfront, that kind of freedom usually hurts more than it helps. Most of the time, simpler workflows with humans in charge still outperform full-blown agents.

I’ve debugged this exact pattern with dozens of teams:

  1. We have multiple tasks that need automation

  2. Agents seem like the obvious solution

  3. We build complex systems with roles and memory

  4. Everything breaks because coordination is harder than we thought

  5. We realize simpler patterns would have worked better

🔎 Takeaway: Start with simpler workflows like chaining or routing unless you know you need memory, delegation, and planning.

These five patterns come from Anthropic’s taxonomy – implemented, tested, and demoed in my notebook:

Use case: “Writing personalized outreach emails based on LinkedIn profiles.”

You want to reach out to people at companies you’re interested in. Start by extracting structured data from a LinkedIn profile (name, role, company), then generate a tailored outreach email to start a conversation.

Here are 3 simple steps:

  1. Turn raw LinkedIn profile text into structured data (e.g., name, title, company):

linkedin_data = extract_structured_data(raw_profile)
  1. Add relevant company context for personalization (e.g., mission, open roles):

company_context = enrich_with_context(linkedin_data)
  1. Generate a personalized outreach email using the structured profile + company context:

email = generate_outreach_email(linkedin_data, company_context)

✅ Use when: Tasks flow sequentially
⚠️ Failure mode: Chain breaks if one step fails
💡 Simple to debug, predictable flow

Use case: Extracting structured data from profiles

Now that chaining works, you want to process many profiles at once and speed up the processing. Split each profile into parts — like education, work history, and skills, then run extract_structured_data() in parallel.

Here are 2 simple steps:

  1. Define tasks to extract key profile fields in parallel:

tasks = [
    extract_work_history(profile),   # Pull out work experience details
    extract_skills(profile),         # Identify listed skills
    extract_education(profile)       # Parse education background
]
  1. Run all tasks concurrently and gather results:

results = await asyncio.gather(*tasks)

✅ Use when: Independent tasks run faster concurrently
⚠️ Failure mode: Race conditions, timeout issues
💡 Great for data extraction across multiple sources

Use case: LLM classifies the input and sends it to a specialized workflow

Say you’re building a support tool that handles product questions, billing issues, and refund requests. Routing logic classifies each message and sends it to the right workflow. If it’s unclear, fall back to a generic handler.

Here are 2 simple steps:

  1. Choose a handler based on profile type:

if profile_type == "executive":
    handler = executive_handler()    # Use specialized logic for executives
elif profile_type == "recruiter":
    handler = recruiter_handler()    # Use recruiter-specific processing
else:
    handler = default_handler()      # Fallback for unknown or generic profiles
  1. Process the profile with the selected handler:

result = handler.process(profile)

✅ Use when: Different inputs need different handling
⚠️ Failure mode: Edge cases fall through routes
💡 Add catch-all routes for unknowns

Use case: LLM breaks down the task into 1 or more dynamic steps

You’re generating outbound emails. The orchestrator classifies the target company as tech or non-tech, then delegates to a specialized worker that crafts the message for that context.

Here are 2 simple steps:

  1. Use LLM to classify the profile as tech or non-tech:

industry = llm_classify(profile_text)
  1. Route to the appropriate worker based on classification:

if industry == "tech":
    email = tech_worker(profile_text, email_routes)
else:
    email = non_tech_worker(profile_text, email_routes)

The orchestrator-worker pattern separates decision-making from execution:

At first glance, this might resemble routing: a classifier picks a path, then a handler runs. But in routing, control is handed off entirely. In this example, the orchestrator retains control: it initiates the classification, selects the worker, and manages the flow from start to finish.

This is a minimal version of the orchestrator-worker pattern:

  • The orchestrator controls the flow, making decisions and coordinating subtasks

  • The workers carry out the specialized steps based on those decisions

You can scale this up with multiple workers, sequential steps, or aggregation logic (and I encourage you to! If you do so, make a PR to the repository), but the core structure stays the same.

✅ Use when: Tasks need specialized handling
⚠️ Failure mode: Orchestrator delegates subtasks poorly or breaks down the task incorrectly
💡 Keep orchestrator logic simple and explicit

Use case: Refining outreach emails to better match your criteria

You’ve got an email generator running, but want to improve tone, structure, or alignment. Add an evaluator that scores each message and, If it doesn’t pass, send it back to the generator with feedback and loop until it meets your bar.

Here are 2 simple steps:

  1. Generate an initial email from the profile:

content = generate_email(profile)
  1. Loop until the email passes the evaluator or hits a retry limit:

while True:
    score = evaluate_email(content)
    if score.overall > 0.8 or score.iterations > 3:
        break
    content = optimize_email(content, score.feedback)

✅ Use when: Output quality matters more than speed
⚠️ Failure mode: Infinite optimization loops
💡 Set clear stop conditions

🔎 Takeaway: Most use cases don’t need agents. They need better workflow structure.

Agents shine when you have a sharp human in the loop. Here’s my hot take: agents excel at unstable workflows where human oversight can catch and correct mistakes.

When agents actually work well:

An agent that writes SQL queries, generates visualizations, and suggests analyses. You’re there to evaluate results and fix logical errors. The agent’s creativity in exploring data beats rigid workflows.

To build something like this, you’d give the LLM access to tools like run_sql_query(), plot_data(), and summarize_insights(). The agent routes between them based on the user’s request — for example, writing a query, running it, visualizing the result, and generating a narrative summary. Then, it feeds the result of each tool call back into another LLM request with its memory context. We walk through a live example of this pattern in our Building with LLMs course.

An agent brainstorming headlines, editing copy, and suggesting structures. The human judges quality and redirects when needed. Agents excel at ideation with human judgment.

Proposing design patterns, catching edge cases, and suggesting optimizations. The developer reviews and approves changes. Agents spot patterns humans miss.

Enterprise Automation
Building stable, reliable software? Don’t use agents. You can’t have an LLM deciding critical workflows in production. Use orchestrator patterns instead.

  • High-Stakes Decisions
    Financial transactions, medical diagnoses, and legal compliance – these need deterministic logic, not LLM guesswork.

Back to my CrewAI research crew: the agents kept forgetting goals and skipping tools. Here’s what I learned:

Failure Point #1: Agents assumed they had context that they didn’t
Problem: Long documents caused the summarizer to forget citations entirely
What I’d do now: Use explicit memory systems, not just role prompts

Failure Point #2: Agents failed to select the right tools
Problem: The researcher ignored the web scraper in favor of a general search
What I’d do now: Constrain choices with explicit tool menus

Failure Point #3: Agents did not handle coordination well
Problem: The coordinator gave up when tasks weren’t clearly scoped
What I’d do now: Build explicit handoff protocols, not free-form delegation

🔎 Takeaway: If you’re building agents, treat them like full software systems. Don’t skip observability.

Table: When to use an LLM, augmented LLM, or Agent (caption)
  • ❌ Agents are overhyped and overused

  • 🔁 Most cases need simple patterns, not agents

  • 🤝 Agents excel in human-in-the-loop scenarios

  • ⚠️ Don’t use agents for stable enterprise systems

  • 🧪 Build with observability and explicit control

Agents are overhyped and often overused. In most real-world applications, simple patterns and direct API calls work better than complex agent frameworks. Agents do have a role—in particular, they shine in human-in-the-loop scenarios where oversight and flexibility are needed. But for stable enterprise systems, they introduce unnecessary complexity and risk. Instead, aim to build with strong observability, clear evaluation loops, and explicit control.

Want to go deeper? I teach a course on the entire LLM software development lifecycle (use code PAUL for $100 off), covering everything from retrieval and evaluation to observability, agents, and production workflows. It’s designed for engineers and teams who want to move fast without getting stuck in proof of concept purgatory.

Use code PAUL for $100 off

If you’d like a taste of the full course, I’ve put together a free 10-part email series on building LLM-powered apps. It walks through practical strategies for escaping proof-of-concept purgatory: one clear, focused email at a time.

Use code PAUL for $100 off

Copyrights: The article was originally published in collaboration with

on – original article.

If not otherwise stated, all images are created by the author.

Source Link


Keep your files stored safely and securely with the SanDisk 2TB Extreme Portable SSD. With over 69,505 ratings and an impressive 4.6 out of 5 stars, this product has been purchased over 8K+ times in the past month. At only $129.99, this Amazon’s Choice product is a must-have for secure file storage.

Help keep private content private with the included password protection featuring 256-bit AES hardware encryption. Order now for just $129.99 on Amazon!


Start your free Amazon Prime trial
today and unlock unlimited streaming and more!

Help Power Techcratic’s Future – Scan To Support

If Techcratic’s content and insights have helped you, consider giving back by supporting the platform with crypto. Every contribution makes a difference, whether it’s for high-quality content, server maintenance, or future updates. Techcratic is constantly evolving, and your support helps drive that progress.

As a solo operator who wears all the hats, creating content, managing the tech, and running the site, your support allows me to stay focused on delivering valuable resources. Your support keeps everything running smoothly and enables me to continue creating the content you love. I’m deeply grateful for your support, it truly means the world to me! Thank you!

BITCOIN

Bitcoin Logo

Bitcoin QR Code

bc1qlszw7elx2qahjwvaryh0tkgg8y68enw30gpvge

Scan the QR code with your crypto wallet app

DOGECOIN

Dogecoin Logo

Dogecoin QR Code

D64GwvvYQxFXYyan3oQCrmWfidf6T3JpBA

Scan the QR code with your crypto wallet app

ETHEREUM

Ethereum Logo

Ethereum QR Code

0xe9BC980DF3d985730dA827996B43E4A62CCBAA7a

Scan the QR code with your crypto wallet app

Please read the Privacy and Security Disclaimer on how Techcratic handles your support.

Disclaimer: As an Amazon Associate, Techcratic may earn from qualifying purchases.

Tags: Hacker News
Share161Share28ShareShare4ShareTweet101
Previous Post

The Elder Scrolls Online director Matt Firor, who helped launch ZeniMax Online Studios in 2007, is leaving the company

Next Post

USA 2-1 Guatemala (Jul 2, 2025) Game Analysis

Hacker News

Hacker News

Stay updated with Hacker News, where technology meets entrepreneurial spirit. Get the latest on tech trends, startup news, and discussions from the tech community. Read the latest updates here at Techcratic.

Related Posts

I’m a physicist by trade, not by training, and that matters | by Chris Ferrie | Jul, 2025
Hacker News

I’m a physicist by trade, not by training, and that matters | by Chris Ferrie | Jul, 2025

July 3, 2025
1.3k
enumura1/chatbot-flow-editor: Visual chatbot flow editor. GUI tool for designing chatbot flows. Create, test, and export as JSON.
Hacker News

enumura1/chatbot-flow-editor: Visual chatbot flow editor. GUI tool for designing chatbot flows. Create, test, and export as JSON.

July 2, 2025
1.3k
Tesla (TSLA) Q2 vehicle deliveries report
Hacker News

Tesla (TSLA) Q2 vehicle deliveries report

July 2, 2025
1.3k
Hackers Target Linux SSH Servers to Deploy TinyProxy and Sing-box Proxy Tools
Hacker News

Hackers Target Linux SSH Servers to Deploy TinyProxy and Sing-box Proxy Tools

July 2, 2025
1.3k
Full-system emulated fuzzing of Qualcomm basebands
Hacker News

Full-system emulated fuzzing of Qualcomm basebands

July 2, 2025
1.3k
Bots Now Account for 30% of Global Web Traffic, Surpassing Human Activity in Some Regions
Hacker News

Bots Now Account for 30% of Global Web Traffic, Surpassing Human Activity in Some Regions

July 2, 2025
1.3k
FileFix Attack Exploits Windows Browser Loophole to Evade Mark-of-the-Web Security
Hacker News

FileFix Attack Exploits Windows Browser Loophole to Evade Mark-of-the-Web Security

July 2, 2025
1.3k
Anthropic MCP Inspector Vulnerability Lets Hackers Run Arbitrary Code Remotely
Hacker News

Anthropic MCP Inspector Vulnerability Lets Hackers Run Arbitrary Code Remotely

July 2, 2025
1.3k
Load More
Next Post
LEVOIT Air Purifier for Home Ad Bottom Google Campaign

USA 2-1 Guatemala (Jul 2, 2025) Game Analysis

Leave a Reply Cancel reply

Your email address will not be published. Required fields are marked *

Your Tech Resources

  • 30 Second Tech ™
  • AI
  • App Zone ™
  • Apple
  • Ars Technica
  • CNET
  • ComputerWorld
  • Crypto News
  • Cybersecurity
  • Endgadget
  • Forbes
  • Fossbytes
  • Gaming
  • GeekWire
  • Gizmodo
  • Google News
  • Hacker News
  • Harvard Tech
  • I Like Cats ™
  • I Like Dogs ™
  • LifeHacker
  • MacRumors
  • Macworld
  • Mashable
  • Microsoft
  • MIT Tech
  • PC World
  • Photofocus
  • Physics
  • Random Tech
  • Retro Rewind ™
  • Robot Report
  • SiliconANGLE
  • SlashGear
  • Smartphone
  • StackSocial
  • Tech Art
  • Tech Careers
  • Tech Deals
  • Techcratic ™
  • TechCrunch
  • Techdirt
  • TechRepublic
  • Techs Got To Eat ™
  • TechSpot
  • Tesla
  • The Verge
  • TNW
  • Trusted Reviews
  • UFO
  • VentureBeat
  • Visual Capitalist
  • Wired
  • ZDNet

Tech News

  • 30 Second Tech ™
  • AI
  • Apple Insider
  • Ars Technica
  • CNET
  • ComputerWorld
  • Crypto News
  • Cybersecurity
  • Endgadget
  • ExtremeTech
  • Fossbytes
  • Gaming
  • GeekWire
  • Gizmodo

Tech News

  • Harvard Tech
  • MacRumors
  • Macworld
  • Mashable
  • Microsoft
  • MIT Tech
  • Physics
  • PC World
  • Random Tech
  • Retro Rewind ™
  • SiliconANGLE
  • SlashGear
  • Smartphone
  • StackSocial
  • Tech Careers

Tech News​

  • Tech Art
  • TechCrunch
  • Techdirt
  • TechRepublic
  • Techs Got To Eat ™
  • TechSpot
  • Tesla
  • The Verge
  • TNW
  • Trusted Reviews
  • UFO
  • VentureBeat
  • Visual Capitalist
  • Wired
  • ZDNet

Site Links

  • About Techcratic
  • Affiliate Disclaimer
  • Affiliate Link Policy
  • Contact Techcratic
  • Dealors Discount Store
  • Privacy and Security Disclaimer
  • Privacy Policy
  • RSS Feed
  • Site Map
  • Support Techcratic
  • Techcratic
  • Tech Deals
  • TOS
  • 𝕏
Click For A Secret Deal

Techcratic – Your All In One Tech Hub © 2020 – 2025
All Rights Reserved
∞

No Result
View All Result
  • 30 Second Tech ™
  • AI
  • App Zone ™
  • Apple
  • Ars Technica
  • CNET
  • Crypto News
  • Cybersecurity
  • Endgadget
  • Gaming
  • I Like Cats ™
  • I Like Dogs ™
  • MacRumors
  • Macworld
  • Tech Deals
  • Techcratic ™
  • Techs Got To Eat ™
  • Tesla
  • UFO
  • Wired