José Miguel Gómez — AI Engineer
AI agents, RAG and MCP on solid backend engineering.
Proof over promises: live products, measured builds.
374 open-source projects built by my autonomous software factory · 82% of 405 work items shipped with no human fix
19 of 19 projects
Featured work
Six projects. Each card opens a case page with its screens.
-
In production Forgeline
From requirement to reviewed PR, governed end to end
Agentic workflow
Turns a feature request into a reviewed pull request: DDD spec, hexagonal code, tests and a security audit.
How it was built: Built in 3.3 h · USD 72.54 of AI · 110 tests · 4 audits
- Now showing
Resolvo
Autonomous incident triage and remediation with human-in-the-loop
Enterprise AI system
Agent-driven triage for enterprise incidents: classify, enrich and route in seconds, with a human in the loop.
-
In production Resonar
Your social media agency, with you as the only approver
Enterprise AI system
A social media agency run by AI agents, with approval queues and per-account budgets. It runs a real LinkedIn account.
How it was built: Built in 2.9 h · 1,183 tests · 2 audits
- Now showing
Specgate
Approved specs in, reviewed code out
Agentic workflow
Delivery intelligence in Go: business-hours flow metrics, QA bugs mapped to OpenAPI contracts, specs served to coding agents over MCP.
How it was built: Built in 3.9 h · 224 tests · 10 audits
-
Coming soon Vigilo
Know what broke, why it matters, and whether it's yours
Developer tool
A vulnerability researcher that matches OSV-Scanner with 1.0 precision and recall on its reference set.
How it was built: Built in 13.3 h · USD 149.75 of AI · 1,350 tests · 5 audits
-
In production Veta
Mining compliance that goes live in days, not months
Enterprise AI system
Contract and compliance platform for mining, built for production with Terraform, Cloud Run and Zero Trust.
How it was built: Built in 4.7 h · 765 tests · 5 audits
No project in this section matches that role.
Products
Products built end to end, each with its own identity and screens.
- Now showing
Tideline
Turn a flood of support tickets into the one incident that matters
Enterprise AI system
Support-ticket intelligence: LLM enrichment behind a privacy gate, incident grouping and idempotent delivery.
How it was built: Built in 3.8 h · 167 tests · 3 audits
-
Coming soon Revela
Raw footage to publish-ready reels: planned by AI, rendered on your machine
Application
Short-video planning and editing: karaoke captions, cuts, reframing and music matched by BPM.
How it was built: Built in 6.8 h · USD 170.93 of AI · 488 tests · 4 audits
-
Coming soon Sublingua
Live translated subtitles for any call, entirely on your laptop
Application
Desktop interpreter and live subtitles for Windows.
How it was built: 1 audit
-
Coming soon Makora
Macros. Clarity. Local.
Application
Local-first nutrition PWA.
How it was built: Built in 2 h · USD 55.46 of AI · 214 tests · 4 audits
-
Now showing Mirador
Every repository at a glance, and what needs your decision today
Developer tool
Observability dashboard for the whole portfolio (public view on synthetic data).
How it was built: 147 tests · 1 audit
No project in this section matches that role.
Lab
Reference builds and katas: the same problem solved more than one way, and measured.
-
Coming soon Aforo
One contract and conformance suite for ten polyglot booking APIs
Developer tool
One API contract, four implementations (Spring Boot, ASP.NET Core, Go, Rails), 379/379 cases each.
How it was built: Built in 13.95 h across 5 repos · conformance 379/379 each
- Coming soon
Kata hexagonal + DDD
One game-jam core on REST, GraphQL and PGlite, measured against layers
Developer tool
One game-jam core on REST, GraphQL and PGlite, measured against layers
How it was built: Built in 4.1 h · USD 85.34 of AI · 425 tests · 4 audits
-
Coming soon KataJam frontend katas
Micro-frontends and five rendering strategies, each measured against the same tests
Experiment
Micro-frontends and five rendering strategies, each measured against the same tests
How it was built: Built in 6.1 h across 2 repos · USD 98.90 of AI · 318 tests · 8 audits
-
Now showing Before and after
Three website redesigns measured with one reproducible audit
Application
Three website redesigns measured with one reproducible audit
How it was built: Built in 1.6 h · USD 38.32 of AI · 190 tests · 4 audits
No project in this section matches that role.
Creative and games
Procedural generation, 3D assets as code, XR and game jams.
-
Coming soon Seedworks
Same seed, same world in C#, C++ and the browser
Developer tool
Same seed, same world in C#, C++ and the browser
How it was built: Built in 2.3 h · USD 52.22 of AI · 397 tests · 4 audits
-
Coming soon Trysac Low-Poly Sampler
Every low-poly asset is a seeded Python script for Blender
Creative tech
Every low-poly asset is a seeded Python script for Blender
How it was built: Built in 1.8 h · USD 33.21 of AI · 233 tests · 4 audits
-
Coming soon XR Showroom
Place low-poly assets in your room or walk among them, no app
Creative tech
Place low-poly assets in your room or walk among them, no app
How it was built: Built in 1.8 h · USD 40.31 of AI · 116 tests · 4 audits
- Now showing
HIT YOUR MARK
A 1930s stunt double performs every take, then directs his own cut
Game
A 1930s stunt double performs every take, then directs his own cut
No project in this section matches that role.
Contact
Available for remote roles and B2B contracts