Orchestration
TypeScript
Agent Director
Cinematic trace debugger for AI agents — playback, replay, diff, and debug agent runs like you're editing video.
JL
Jason Lovell
I build AI agents. I also advise execs on whether they should.
Agentic AI engineering, multi-agent orchestration, and enterprise strategy. 20+ years bridging the gap between deep tech and the boardroom.
3
Published Standards
20+
Open Source Repos
20+
Years in Tech
Texas
About
20+ years in tech across consumer, industrial, TMT, and public sectors — UK and US. For most of that, my job was translating what engineers build into something a CFO cares about. New revenue. Lower costs. Better experiences.
Then I stopped just advising and started building. Agentic systems with Claude Code and Codex. Multi-agent orchestration. Autonomous triage engines. I've broken enough prototypes at 11pm to know what works versus what looks good in a demo.
The market is full of people who can talk about AI, and people who can build it. I do both. TEDx speaker. Three DOI-registered open-source standards. 20+ public repos and growing fast.
TEDx
Speaker
3
Published Standards
20+
Years · UK & US
20+
Open Source Repos
Focus Areas
Agentic AI EngineeringEnterprise AI StrategyLLM Tooling & OrchestrationMulti-Agent SystemsAI Agent SecurityC-Suite Advisory
Open Source
Projects
From agent orchestration to observability tooling — building at the intersection of AI capability and production readiness.
Orchestration
1
TypeScript
ABCP
Standards-first control plane for agentic browser actions across Gemini Computer Use, AWS Bedrock AgentCore, and ChatGPT Atlas.
Orchestration
Python
Switchboard
Multi-provider agent orchestration sandbox — OpenAI, AWS Bedrock, Google Vertex with policy-based approvals and cryptographic audit trails.
Observability
Python
SkillScope
Observability for Anthropic Skills — see which skill was intended, files referenced, policy approvals, and token/latency shifts.
Observability
Python
AMDM
End-to-end toolkit for observing agentic systems — detecting emergent anomalies in near-real time and benchmarking detector performance.
Observability
Python
MCP Interop BakeOff
Research-grade harness for stress-testing MCP servers across multiple agent runtimes with reproducible task suites.
Governance
TypeScript
Sentinel MCP
Governing Model-Context Protocol servers with policies, budgets, and verifiable provenance.
Governance
TypeScript
Agent HQ Guard
GitHub App and Action enforcing policy, provenance, and budget controls across autonomous agent runs. CI/CD guards for AI.
Governance
Python
SKILLCHECK
Safety-first auditor for Agent Skills — examine any skill bundle before enabling it with repeatable, standards-aligned checks.
Applied AI
Python
OverhearOps
Agentic system that overhears Teams conversations, detects actionable threads, and drafts remediation artefacts with full observability.
Applied AI
Python
TerraRisk Agent
Geospatial AI governance research — FEMA NRI, BigQuery Earth Engine, and satellite imagery with auditable, policy-enforced outputs.
Applied AI
3
Python
VoiceForge AI
Intelligent emotion detection for TTS — Mistral 7B analyzes context and sarcasm to generate emotionally aware speech.
Standards & Research
Publications
Contributing to the foundations of trustworthy AI — standards, RFCs, and research that shape how agents operate safely at scale.
Standard2025
TBOM: Tool Bill of Materials
A provenance and integrity standard for the MCP ecosystem. Cryptographically signed manifests that bind MCP server releases to immutable tool metadata, enabling automated trust verification and preventing tool poisoning in AI agent supply chains.
Standard2026
SBA: Skill Bundle Attestation
Deterministic bundle identity, content attestation format, and verification tooling for agent skill bundles. Minimal, reproducible, and supply-chain friendly — enabling trust at the skill layer.
Standard2026
TSA: Tool Security Advisory
Machine-readable security advisories for MCP tools. Defines a JSON format, feed index, and trust model for registries, hosts, and gateways to automatically block, warn, or remediate vulnerable tools.