Blog

Research findings, compliance guidance, and engineering insights.

2026-05-20Research

SCITT as the Article 12 Implementation Pattern for Autonomous AI Agents

EU AI Act Article 12 requires logs conformant to recognised standards. SCITT is the IETF-track standard designed for this evidence shape. The article-by-article mapping, the gaps SCITT explicitly leaves open, and a concrete implementation pattern.

2026-05-06Engineering

/llms.txt is not enough: a discovery suite for agent-facing APIs

A single Markdown file cannot carry everything an agent needs to plan a session against an API. Five surfaces — link index, OpenAPI, agent-card, scope profiles, verification keys — and one principle: predictable availability.

2026-05-06Engineering

The advisory-lock self-deadlock Postgres can't see

PostgreSQL's deadlock detector walks the row-lock wait graph. Advisory locks held across `await` boundaries can form cycles through application code that the detector cannot see. Reproduction, real diagnostic output, and the structural fix.

2026-05-06Engineering

Near Frontier-Quality LLM, No Cloud, No Subscription, Unlimited Tokens: gpt-oss:120b on Strix Halo + Ubuntu 26.04

A 96 GB Strix Halo box arrived in 4 days, runs gpt-oss:120b at 35 tok/s on Ubuntu 26.04, and draws 40-140W. The three kernel parameters every 2025-era guide misses, the benchmark table, and a runnable bench script.

2026-05-03Engineering

pg-boss in production: footguns we hit and how to avoid them

Four operational footguns we hit running pg-boss at AGLedger for about a year. One is fixed upstream; the other three still bite. Self-contained reproductions, citations, and the patterns we settled on.

2026-04-19Research

Why receipts must be signed: a threat model for agent accountability

Logging answers "what happened?" Signed receipts answer "can you prove it to someone who does not trust you?" Four scenarios where logs quietly fail and what signing buys you mechanically.

2026-04-18Engineering

Cutting PostgreSQL Audit-Report Query Time 44% with GROUPING SETS and Materialized CTEs

Six aggregations per request became two. Total DB time dropped 44% under sustained load. The anti-pattern, the rewrite, and the honest caveat about why wall-clock p50 did not move.

2026-04-15Research

Frictionless Compliance: How Accountability Gates Guide AI Agents to Success

70 traces, 4 LLM providers. A bare policy denial causes agents to fabricate, quit, or loop. Add a directive and AGLedger tools — agents complete the full accountability lifecycle. No system prompt changes.

2026-04-13Research

What We Learned Adapting to Google A2A v1.0

27 experiments, 30 multi-agent runs. A2A handles task delegation. It does not handle accountability. Here is what the data shows and how AGLedger bridges the gap.

2026-04-13Engineering

Zero Mocks, Real Infrastructure: How AGLedger Tests an Accountability Engine

36 tests against a live API. Real EKS, real Aurora, real webhooks, real LLM agents. Why we deleted 117 tests last week and what the testbed covers now.

2026-04-10Research

Zero Dispatcher Calls: When Accountability Became the Coordination Layer

We removed the task dispatcher from a 3-agent system. Instead of breaking, agents coordinated entirely through accountability tools — 56 receipts, 41 auto-settled, 0 dispatcher calls.

2026-04-07Security

We Published Our Security Whitepaper

AGLedger's security architecture is now public. 18 sections covering trust boundaries, cryptographic design, threat model, compliance mappings, and post-quantum readiness.

2026-04-06Research

Designing APIs for AI Agents: Lessons from 3 LLM Providers

36 tools tanked completion to 0%. 10 focused tools achieved full lifecycle closure. What we learned testing Claude, GPT, and Gemini against the same API.

2026-04-06Research

Budget LLMs Outperform Premium Models at Task Completion

Haiku and GPT-4o-mini beat Sonnet and GPT-4o at actually finishing work. The "Doers vs Planners" phenomenon.

2026-04-06Research

Zero-Scaffolding API Discovery: Can Agents Learn Your API from Scratch?

HTTP + llms.txt achieved 100% record lifecycle completion. SDK achieved 0%. What this means for API design.

2026-05-19Engineering

60 Records per Second on a Single Replica: AGLedger Performance at Scale

v0.23.0 stamp on the smallest AWS footprint we could deploy. 60 RPS notarize-only sustained, 12 RPS full gated lifecycle, 100% chain integrity under load.

2026-04-06Compliance

EU AI Act Article 12: What Event Logging Actually Requires for AI Agents

A deep dive into Article 12 event logging requirements and how structured accountability records satisfy them automatically.

2026-04-06Compliance

NIST AI RMF for AI Agent Operations: A Practical Mapping

How the four NIST AI RMF functions — GOVERN, MAP, MEASURE, MANAGE — map to agent accountability infrastructure.

2026-04-06Compliance

ISO 42001 Certification Evidence: What Auditors Actually Want to See

Practical guidance on generating ISO/IEC 42001:2023 certification evidence as a byproduct of AI agent operations.