Forum

Discuss agent architectures and share learnings with the community.

Share your knowledge

Write about agent architectures, share evaluations, or ask the community.

AgenticWorks

A community for developers awakening to agentic AI. Hands-on lessons, enterprise-grade context engineering, and a forum that earns its quiet.

Platform

  • Learn
  • Forum
  • Showcase

Project

  • About

Community

  • Network
  • Code of conduct

Field reports

Monthly notes on what shipped, what broke, and what we learned.

© 2026 AgenticWorks. Built in public.

RisingNewTop Signal
AgenticWorks
LearnShowcaseForumCommunity
Sign in
Cover image for "Episodic logs are not structured state."
IM
Ingrid Martinez8/26/2025
Senior Solutions Architect · Agriculture
article

Episodic logs are not structured state.

Short-term scratchpads, long-term knowledge stores, and session boundaries each solve different problems. Treating chat history as memory is why your agent forgets what mattered.

#agents#memory#context-engineering#workflow#architecture
4
Cover image for "Two research projects converged into one enterprise SDK."
ML
Mateo Lee4/14/2026
Senior Solutions Architect · LegalTech
article

Two research projects converged into one enterprise SDK.

AutoGen taught Microsoft conversation loops; Semantic Kernel taught it enterprise plumbing. The Agent Framework is the merger, and the migration story matters more than the feature list.

#microsoft#autogen#frameworks#agents#orchestration
4
Cover image for "The enterprise agent play is governance, not models."
PH
Pavel Hernandez4/24/2026
Agent Platform Engineer · Healthcare
article

The enterprise agent play is governance, not models.

Cloud Next was less about a new model and more about where agents run, who governs them, and how they get discovered inside an org. Here's what Agentspace and the ADK push mean for enterprise buyers.

#google#news#agents#deployment#frameworks
3
Cover image for "State machines beat agent improv."
TA
Tessa Anderson6/3/2025
Developer Advocate · Manufacturing
article

State machines beat agent improv.

Letting agents riff produces great demos and terrible audits. Explicit planner–worker–critic loops encode rejection at the orchestration layer. The same move as scaling-your-no, but structural.

#orchestration#agents#eval#workflow#architecture
4
Cover image for "Parsing is the product. Embeddings are the commodity."
RV
Ravi Vargas10/7/2025
Search & Retrieval Engineer · Transportation
article

Parsing is the product. Embeddings are the commodity.

I've replaced three 'RAG is solved' pipelines this year. The pattern is always the same: layout-aware parsing, hybrid retrieval, and a reranker, not a bigger embedding model.

#rag#pdf-parsing#context-engineering#agents#workflow
4
Cover image for "Hooks intercept. Skills package judgment."
BE
Beatriz Eze5/13/2025
Associate ML Engineer · Education
article

Hooks intercept. Skills package judgment.

Everyone name-drops hooks and skills. Almost nobody explains when to use which, and conflating them builds brittle agents that break on the second edge case.

#agents#skills#hooks#workflow#engineering
4
Cover image for "Token counts don't explain tool failures."
AB
Aisha Bennett5/19/2026
Staff Reliability Engineer · Energy
article

Token counts don't explain tool failures.

Agent observability needs span-level tool attribution, critic decisions, and replayable traces, not aggregate token dashboards that hide the fork where everything went wrong.

#observability#agents#mlops#workflow#eval
4
Cover image for "An agent isn't a chat loop with tools bolted on."
QU
Quinn Ueda4/8/2025
Staff ML Engineer · E-commerce
article

An agent isn't a chat loop with tools bolted on.

Model, memory, tools, planner, orchestrator, eval: six components with explicit contracts between them. Skip the contracts and you get a demo that collapses in week two.

#agents#architecture#orchestration#skills#workflow
5
Cover image for "The hallway track was about evals, not agents."
WB
Wei Bakshi5/15/2026
Solutions Engineer · Telecom
article

The hallway track was about evals, not agents.

Interrupt's main-stage energy was multi-agent, but the practitioner conversations kept circling back to evaluation, tracing, and the boring reliability work. That gap is the real signal.

#langchain#news#agents#frameworks#eval
4
Y
Yoha2/11/2025
Founder · Agentic AI
article

Chatting with a model isn't a skill. Programming an agent is.

Five learnable skills and two frameworks that separate the people writing their own ticket from the people sending out their hundredth résumé.

#agents#career#skills#orchestration#eval
6
Cover image for "Compliance teams care about the data plane."
KO
Keiko Okafor2/10/2026
Junior Developer (Career Transition) · Nonprofit
article

Compliance teams care about the data plane.

Self-hosted agents trade API convenience for data-plane control. For regulated industries that's not ideology; it's the only architecture legal will sign.

#agents#deployment#workflow#engineering#cost
4
Cover image for "Framework choice is a state-management bet."
KO
Keiko Okafor, BS3/3/2026
Solutions Engineer · Nonprofit
article

Framework choice is a state-management bet.

LangGraph makes state explicit; CrewAI abstracts roles. Neither is 'better'. The choice is whether your team needs inspectable graphs or faster role-based prototyping.

#langgraph#crewai#orchestration#agents#workflow
12
Cover image for "Vector search on CSV-shaped text is a trap."
DB
Deepa Brooks10/28/2025
Senior RAG Engineer · PropTech
article

Vector search on CSV-shaped text is a trap.

Tabular enterprise data needs schema-aware retrieval, SQL or semantic layers, and explicit join logic. Dumping rows into chunks and embedding them is why agents confidently cite the wrong quarter.

#rag#agents#context-engineering#workflow#engineering
3
Cover image for "Same model tier on every step kills ROI."
OS
Omar Singh, Bootcamp Certificate3/24/2026
MLOps Engineer · Consulting
article

Same model tier on every step kills ROI.

If your planner, worker, and critic all hit a frontier model, your margin dies. Cost architecture; model routing by task criticality: is as important as prompt architecture.

#cost#agents#mlops#orchestration#workflow
4
Cover image for "The platform is only as good as the traces you feed it."
EI
Elena Ibrahim6/4/2026
MLOps Engineer · Hospitality
article

The platform is only as good as the traces you feed it.

LangSmith gives you tracing, datasets, and online evals out of the box. The teams that get value wire production failures back into golden datasets. Here's the loop, end to end.

#langsmith#observability#eval#agents#mlops
4
Cover image for "Lock-in moves to tool registries."
HL
Hassan Lopez6/2/2026
Staff Applied Researcher · Pharmaceuticals
article

Lock-in moves to tool registries.

MCP standardization is real, but so is registry sprawl. The enterprise risk isn't picking the wrong model. It's building on a tool catalog you don't control.

#mcp#agents#workflow#engineering#eval
4
Cover image for "Everyone shipped governance. Nobody shipped certainty."
OJ
Olivia Jackson5/29/2026
Technical Product Manager · Supply Chain
article

Everyone shipped governance. Nobody shipped certainty.

I/O, Cloud Next, Build, re:Invent, and Interrupt across one season. The throughline isn't a winning framework; it's that the whole industry quietly admitted reliability and governance are the unsolved part.

#news#agents#frameworks#frontier-models#workflow
4
Cover image for "Golden traces beat prompt tweaks."
CG
Chen Garcia6/24/2025
ML Platform Lead · Legal
article

Golden traces beat prompt tweaks.

An eval harness isn't a leaderboard; it's rejection infrastructure. Golden traces, regression suites, and critic gates turn encoded judgment into CI for your agents.

#eval#agents#workflow#orchestration#engineering
4
Cover image for "Four names, four jobs. Lets stop conflating them."
MQ
Maria Quinn7/15/2025
Community Engineer · Gaming
article

Four names, four jobs. Lets stop conflating them.

The LangChain brand spans an abstraction library, a graph runtime, an eval/observability platform, and an expression language. Teams that blur them ship the wrong tool for the layer. Here's the clean mental model.

#langchain#frameworks#agents#orchestration#engineering
4
Cover image for "Idempotent tools, retry-owning workflows."
FW
Freya Wright1/27/2026
Workflow Architect · Climate Tech
article

Idempotent tools, retry-owning workflows.

Glue-code automation wins when MCP tools are idempotent and the workflow owns retries, not when you chain hopeful API calls and pray the agent recovers.

#mcp#agents#workflow#tools#engineering
4