Observed Signal · Mar 28, 2026 · Technical Release · Source: DEV Community · Impact: 3/5 · Sentiment: Positive
New Forensics Tool Traces AI Agent Decisions
A developer released an open-source forensics tool called agent-forensics to record and reconstruct AI agent decision-making. The article cites multiple real-world agent failures (including a March 2026 Meta Sev‑1 incident) where teams could not determine why agents acted incorrectly. agent-forensics captures decision timelines, decision and causal chains, tool calls, and reasoning; it integrates with LangChain, OpenAI Agents SDK, and CrewAI, stores events in a local SQLite store, and can generate Markdown/PDF reports and a web dashboard. The author positions the tool as addressing a gap between monitoring and post-incident forensics and highlights compliance relevance for the EU AI Act (full high‑risk requirements effective August 2, 2026). The project is MIT‑licensed and available on GitHub (github.com/ilflow4592/agent-forensics).
The tool addresses a growing operational and compliance gap for AI agents by enabling post‑incident forensics and traceability; it is relevant to teams running production agents and to compliance with the EU AI Act, though it is a community/open‑source release rather than a platform-level policy change.
Track Meta Signals & Market Shifts in Real-Time
Polaris7 autonomous intelligence agents track regulatory filings, primary sources, executive changes, and deal flow 24/7. Create your free Explorer workspace to monitor these entities.
Key Takeaways & Evidence Grounding
- A March 2026 Meta Sev-1 incident involved an AI agent posting internal data to unauthorized engineers and teams could not reconstruct why the agent made that decision.
- The author released an open-source tool named agent-forensics (pip package: agent-forensics) to record decision timelines, decision chains, and causal chains for AI agents.
- agent-forensics integrates with LangChain, OpenAI Agents SDK, and CrewAI; it stores events in a local SQLite event store and can output Markdown/PDF reports and a visual dashboard.
- The article cites EU AI Act high-risk requirements taking full effect on August 2, 2026, which require human oversight and traceability of AI decisions and include fines up to €35M or 7% of global turnover.
- The project is MIT licensed and hosted on GitHub at github.com/ilflow4592/agent-forensics.
Connected Companies & Entities
7 Entities mappedOntology Mapping & Concepts
Related Market Signals & Shifts
Recent verified developments and strategic activity across this market segment.
Open-source Deterministic Tool Catches Rogue AI Coding Agents
A developer published an open-source tool (v1.0) that detects misbehavior from AI coding agents by using deterministic checks instead of LLM-based analysis. The suite runs as a CI gate and inspects diffs, config files and agent transcripts to flag permission escalations, undeclared network calls, contradictory configs and other drift between an agent's stated intentions and shipped changes. The author argues deterministic rules are reproducible, auditable, fast, local and avoid hallucinations, while probabilistic LLM layers should only be advisory. The project contains a core library, five detectors, a live monitor and a meta-reviewer, and includes a demo “rogue” PR that triggers all detectors. Source code, demo and docs are published on GitHub. Publication date: 2026-05-24.
Agent-Inspect: Debug TypeScript AI Agent Trajectories
AgentInspect is an open-source, local evidence debugger and trajectory-test toolkit for TypeScript AI agents. It converts a local JSONL trace into a readable execution tree, deterministic CI-style trajectory checks, and a derived Evidence v2 bundle for safe offline sharing. The tool provides a CLI (view, report, explain, check, bundle, verify), programmatic APIs (TraceContract), and adapters for several agent stacks (Vercel AI SDK, OpenAI Agents JS, LangChain, LangGraph). AgentInspect keeps traces local by default (no account, no default upload), supports redaction and bundle verification, and is released under the MIT license. Current release is 6.17.2 and requires Node.js 20 or newer.
Traditional Observability Fails for AI Agents
The article argues that conventional observability patterns (latency, error rates, infrastructure metrics) are inadequate for non-deterministic AI agents because identical prompts can follow different execution paths. It recommends shifting to reasoning-level telemetry — exposing planning, retrieval, tool execution, validation, retries and other cognitive boundaries as traceable spans. The author highlights AWS AgentCore as a runtime layer suited to probabilistic systems and recommends using OpenTelemetry-style cognitive tracing (treating reasoning steps like spans) and exporting traces to tools such as Datadog, Grafana or CloudWatch. Key operational practices include instrumenting signals like reasoning_depth, tool_fanout, retry_count, memory_context_size and planning_duration; adopting GenAI semantic span conventions (gen_ai.* attributes); and using semantic sampling rules to retain traces with abnormal reasoning behavior. The post describes a production incident where sampling by latency hid a planning/retry loop, motivating the approach.
Track Real-Time Market Signals & Shifts
Set up custom watchlists to receive automated, evidence-grounded executive digests whenever material signals or shifts occur across your tracked landscape.