Skip to main content
alongside
P

Author

Pedro Pinho

Chief Executive Officer

Articles by Pedro Pinho

engineering
engineering·3 min read

Claude Opus 5.5 vs Grok 4.7 vs GPT-6 Astra: Which Frontier Model for Coding Agents?

Opus 5.5 for long agentic coding, Grok 4.7 for low token cost, GPT-6 Astra for computer use and the largest context. And why Astra 6.1 never shipped.

Pedro Pinho·04/Oct/2026
claude opus 5.5 vs grok 4.7 vs gpt-6 astraopus 5.5 vs gpt-6 astragrok 4.7gpt-6.1 astraterminal-bench 4.0
engineering
engineering·3 min read

Grok Bot vs Muse: Same Cloud Computer Idea, Different Trust Boundaries

Grok Bot and Meta's Muse both give an agent a persistent cloud computer. The real difference is where the trust boundary sits: around a shared per-user machine, or beneath the agent itself.

Pedro Pinho·04/Oct/2026
ai agentsgrok botmuseagent securitysandboxing
engineering
engineering·3 min read

Best AI Coding Agent Harness in 2026: Claude Code vs Codex vs OpenCode

Codex CLI is our default coding agent harness for most teams in October 2026. Claude Code ties it on Terminal-Bench 4.0, OpenCode wins on model choice. Here is how they compare on sandboxing, extensibility and cost.

Pedro Pinho·04/Oct/2026
best ai coding agentai coding agent harnessclaude code vs codexopencodeterminal-bench
engineering
engineering·3 min read

Railway's Five-Minute 404: When a Failed Lookup Looks Like a Missing Route

On 30 September 2026, Railway returned 404 for every new connection for five minutes. A deploy beat its schema migration, and a failed lookup was reported as a missing route.

Pedro Pinho·04/Oct/2026
incident analysisdatabase migrationsdeploymentdistributed systemsreliability
tutorials
tutorials·3 min read

Your First Agent with Hermes or OpenClaw: Install, Lock Down, Schedule

A practical first day with Hermes Agent or OpenClaw: one clean chat, one skill, and one scheduled pull request digest. Then the security settings to check before you connect a chat app.

Pedro Pinho·04/Oct/2026
ai agentshermes agentopenclawagent skillsautomation
What AMÁLIA Teaches Us About Building Portuguese AI
industry insights·3 min read

What AMÁLIA Teaches Us About Building Portuguese AI

Portugal’s AMÁLIA LLM is a strong step toward European Portuguese AI. The bigger lesson: useful national AI needs open models, local data, and better evaluation.

Pedro Pinho·02/Jul/2026
aillmsportugaldata-strategyeuropean-portuguese
How to Secure and Observe Agent Memory in Production
tutorials·5 min read

How to Secure and Observe Agent Memory in Production

A practical guide to securing and monitoring agent memory in production, from access control and audit trails to runtime visibility and retention discipline.

Pedro Pinho·19/May/2026
agent-securityobservabilityagent-memorypostgresqlauditability
Redis and PostgreSQL Together for AI Agents: Cache Fast, Store Truth in Postgres
tutorials·5 min read

Redis and PostgreSQL Together for AI Agents: Cache Fast, Store Truth in Postgres

A practical hybrid architecture for AI agents: use PostgreSQL for durable workflow truth and Redis for the short-lived acceleration layers that actually need it.

Pedro Pinho·19/May/2026
redis-postgresqlai-agentscachesession-statehybrid-architecture
How to Migrate Agent Memory from Redis to PostgreSQL Without Breaking Sessions
tutorials·5 min read

How to Migrate Agent Memory from Redis to PostgreSQL Without Breaking Sessions

A practical migration path for teams moving agent memory from Redis to PostgreSQL without risking broken sessions, messy cutovers, or silent state loss.

Pedro Pinho·19/May/2026
redis-migrationpostgresqlagent-memorysession-statecutover
How to Design a PostgreSQL Schema for Agent Memory and Session State
tutorials·6 min read

How to Design a PostgreSQL Schema for Agent Memory and Session State

A practical guide to modelling agent sessions, messages, tool runs, and memory snapshots in PostgreSQL without turning production state into one giant JSON blob.

Pedro Pinho·19/May/2026
postgresql-schemaagent-memorysession-stateai-agentsjsonb