━━ failproof ai · field guides
guides
every failproof guide and how-to in one place - the specific fix for the specific failure. stop dangerous commands, block rm -rf, keep secrets out of the context window, handle agent failures, and observe, replay, and query every run.
━━ specific failure modes
- f·1
AI agent stuck in a loop - how to break it
Why coding agents retry the same failing step forever, how to detect the loop, and the hook-level policy that breaks it, summarizes progress, and restarts clean.
→ - f·2
Agent hallucinated a tool or file - how to stop it
When the agent calls a tool, file, or API that does not exist, block the invented call at the hook layer and hand the agent what does exist nearby instead.
→ - f·3
Agent context drift - keep agents on task
Agents wander off the original goal as context fills up. Detect the drift and pull the agent back to what it was actually asked to do, at the hook layer.
→ - f·4
Agent won't stop after finishing - how to end the run
The task is done but the agent keeps going, editing more, spending more, risking more. Stop the run the moment intent is complete and surface the result.
→
━━ reliability & failure handling
- g·1
AI failure handling for production agents
The five failure categories, why retries don't cut it, and how harness hooks become the enforcement primitive.
→ - g·2
LLM agent reliability - closing the production gap
The reliability gap between demo and production, the 3U framework, and hook-level enforcement across every supported harness.
→ - g·3
Agent error recovery - detect, mitigate, continue
The retry / repair / block taxonomy and the recovery strategy mapped to every failure mode failproof catches.
→
━━ safety & policy enforcement
- g·4
How to stop Claude Code from running dangerous commands
Install failproof, register the PreToolUse hooks, and the destructive command classes - rm -rf, sudo, curl | sh, force push, terraform destroy - stop at the hook layer.
→ - g·5
Claude Code safety hooks - complete setup guide
PreToolUse, PostToolUse, Stop. The 39 built-in policies grouped by category. Three configuration scopes. Custom JS policies.
→ - g·6
How to block rm -rf in Claude Code
The block-rm-rf policy in detail - every recursive flag shape it catches, the safe-path allowlist, and what the agent sees when a delete is denied.
→ - g·7
How to prevent Claude Code from accessing .env files
Two PreToolUse blockers plus five PostToolUse sanitizers - keep secrets out of the agent context window, even when the agent legitimately reads a related file.
→ - g·8
How to prevent AI agent force push
block-force-push, block-push-master, block-work-on-main. One engine, every harness - Claude Code, Codex, Cursor, Gemini CLI, Copilot, picode, opencode.
→ - g·9
How to sandbox Claude Code terminal access
Policy sandbox without a container or VM - PreToolUse confinement, PostToolUse sanitization, Stop gates. Stack a container on top only when you need a kernel boundary too.
→
━━ observability & debugging
- g·10
AI agent observability - see what your agents did
Why logs aren't enough for agents, the four pieces of real observability - live event stream, session replay, queries, alerts - and how failproof ai ingests every run in realtime.
→ - g·11
Agent session replay - debug every run span by span
Replay any run on the trace rail, expand a span to the raw model or tool call, and see exactly where the agent looped, drifted, or got blocked.
→ - g·12
Query agent traces in SQL
SQL and a visual builder over every event, session, and eval - find failure patterns across thousands of runs, save them to dashboards, and turn them into alerts.
→ - g·13
Agent failure alerting - catch breaks in real time
Trigger on a metric, a saved query, or an eval score; open an incident your team can triage; and pull the alert into your local Claude via the CLI and MCP.
→ - g·14
How to add observability to your Hermes agent in 60 seconds
Hermes runs behind a chat gateway when nobody is watching. Two commands - an install and failproofai config - forward every tool call, model request and error to a dashboard you can replay.
→
━━ decision models
- g·15
Decision-model launches after Jev
OpenAI announced a decisions API. Cloudflare and Perplexity published routes. Here is what you can inspect or call as of October 2.
→ - g·16
Jev vs Perplexity Decisions API
Perplexity has a callable decisions endpoint and open weights. See where its contract and price differ from Jev.
→ - g·17
Jev vs OpenAI Decisions API
OpenAI named a Decisions API at DevDay. The public request shape and price are still missing. Here is the test to prepare.
→ - g·18
Jev vs Cloudflare Clef
Clef accepts Jev-style questions and publishes weights. Cloudflare’s own benchmark table has wins on both sides.
→ - g·19
Jev vs Laya
Laya runs locally and routes among language checkpoints. Test the actual languages and scripts in your queue.
→ - g·20
Jev vs Kev-9B
Kev-9B serves a familiar API on local hardware. Its probabilities and thresholds need their own test.
→ - g·21
Jev vs Intern-Decision
InternLM has open checkpoints with image input. A fair Jev comparison has to account for what each model saw.
→ - g·22
Jev vs Julia 1
Julia 1 can run on CPU or WebGPU. Its 2–20 option limit and borrowed Jev benchmark figures matter.
→ - g·23
Jev evals in DeepEval
DeepEval can turn Jev questions into a metric. The resulting score means what your weights define.
→ - g·24
Jev eval platforms compared
Which tool keeps the question, trace and bad verdict after the run? Compare the Jev eval workflows.
→
━━ roundups & how-tos
- ★
8 Best AI Agent Observability Platforms (2026)
A deep comparison of the platforms teams use to trace, evaluate, and govern AI agents in production - what each does, where it stops, and which fits your stack.
→ - ★
How to Make AI Agents Reliable and Follow Instructions (2026)
Agent reliability is a few distinct jobs, not one feature. The tools and approaches that cover each - observability, evals, guardrails, durable execution, and runtime enforcement - and how to combine them.
→