Dan Mercede (Dan-Mercede)

Founder building governed AI systems: fail-closed execution, audit-grade receipts, agent infrastructure, and reliable automation.

Escondido, California, United States
Website
GitHub
Twitter

Fork Around & Find Out — Fork Around & Find Out

Terraform plan, but for agent actions: every risky tool-call runs first in a disposable Daytona sandbox, gets measured, and is cleared to run for real only if it passes a fail-closed policy gate.

Notary — Notary

The context lie detector for your DataHub catalog

Proctor — the agent that QAs other agents — Proctor — the agent that QAs other agents

QA for non-deterministic AI agents: Proctor learns each automation's behavioral contract, catches silent model/prompt regressions, and escalates real failures to a human — all governed by UiPath.

Whisperways — Whisperways

Noise-aware eVTOL corridors: route flight by who hears it

Codex Rule Ledger — Codex Rule Ledger

Evidence-bound audits for Codex runs: support, contradict, or admit the evidence cannot decide.

engram — engram

A memory engine for AI agents: typed memories, budget-bounded recall, timelyforgetting, and contradiction adjudication. Built on Qwen Cloud.

Plainspeak — Plainspeak

AI that reads the fine print for you: paste any dense document and get it in plain words, the parts that affect you, and the questions to ask before you sign.

Quorum — Quorum

Decisions vanish in Slack threads. Quorum detects them, drafts a record, gets one-click approval, files it to a Canvas, and answers 'what did we decide about X?' with cited sources.

Impact Lens — Impact Lens

What does changing this break? Blast-radius analysis on the GitLab Orbit knowledge graph — every definition, file & test that depends on a symbol, with a risk score and the tests to re-run.

Aegis — The Release Gate for AI Agents — Aegis — The Release Gate for AI Agents

Gemini 3 reads your AI agent's own traces, catches runtime regressions CI can't, and blocks the release. A human approves or overrides, every decision recorded for audit.

algorithm.reviews — The Agent Trust Layer — algorithm.reviews — The Agent Trust Layer

A governed AI agent that fact-checks any claim against the live web, shows every source it admits or rejects in real time, and ships a cryptographically signed receipt you can verify.