Ai-Agents on David Lang

Building Reliable AI Agents: Lessons from Production

Sat, 28 Feb 2026 00:00:00 +0000

Production agents fail in boring ways: timeouts, tool errors, runaway loops, and silent wrong answers. Reliability engineering applies to agents too.

Hardening Checklist

Max steps and token budgets per session
Idempotent tools with clear error messages
Checkpoint state for long workflows
Circuit breakers when external APIs fail
Structured logging of every tool call

Graceful Degradation

When the agent fails, fall back to search-only RAG or human handoff-never an empty error.

From RAG to Agentic AI: What's Next for LLM-Powered Apps

Mon, 01 Dec 2025 00:00:00 +0000

The industry moved from chatbots → RAG → agents. Understanding the progression helps you invest in the right layer for your product maturity.

RAG Era

Ground models in private data. Mature patterns: chunking, hybrid search, citations. Still the right default for Q&A and search.

Agent Era

Models call tools, plan multi-step workflows, and maintain state. Higher capability, higher risk.

What’s Next

Evals-as-code in every pipeline
Smaller specialist models routed by orchestrators
On-device for privacy-sensitive steps
Human-agent collaboration UIs, not just chat

Migration Path

Master RAG and evals first. Add one well-scoped agent tool. Measure task completion before expanding autonomy.

Building Multi-Agent AI Systems

Tue, 20 May 2025 00:00:00 +0000

Multi-agent systems divide work among specialized agents-a researcher, coder, critic-coordinated by a supervisor or message bus.

Patterns

Supervisor - One model delegates subtasks and aggregates results.

Peer-to-peer - Agents message each other until consensus or max rounds.

Pipeline - Fixed stages (plan → implement → test).

Implementation Tips

Give each agent a narrow system prompt and tool set. Pass structured state (JSON) between agents, not raw chat logs.

Failure Modes

Infinite loops, duplicated work, conflicting edits. Enforce step limits, idempotent tools, and single-writer rules for shared files.

Building AI Agents with LangChain and OpenAI

Sun, 28 Jul 2024 00:00:00 +0000

AI agents loop: observe, plan, act with tools, observe again. They handle multi-step tasks like research, booking, or code changes.

Tool Definition

from langchain.tools import tool

@tool
def search_docs(query: str) -> str:
    '''Search internal documentation.'''
    return vector_store.similarity_search(query, k=5)

Bind tools to the model; the model returns tool calls you execute and feed back as observations.

Control and Safety

Set max iterations. Require human approval for destructive tools. Log every step for audit.

Conclusion

Agents are powerful and unpredictable. Start with a fixed workflow (chain); graduate to agents when the task path genuinely varies per request.