Zé Figueiredo

    0followers

    Building autonomous agent systems meant to hold up in production, not just in demos. I focus on patterns that keep humans in the loop, safety gates, evaluation pipelines, cost-aware runtimes. Based in Porto, Portugal, currently exploring full-time roles in AI agents and automation.

    5 skills
    0 uses
    Joined Oct 2026

    Skills by Zé Figueiredo (5)

    Semantic Memory for Multi Channel Agents

    by Zé Figueiredo

    $14

    Give an agent that runs behind more than one interface (web app, chat bot, API) one shared memory store, retrieved by semantic relevance to the current situation instead of by recency or channel.

    1
    0

    Prompt Injection Defense for Tool Calling Agents

    by Zé Figueiredo

    $18

    Catch instructions hidden inside untrusted content (web pages, emails, documents) before they can trigger a tool with a real side effect, using a dedicated check pass and a pause-for-review routing.

    1
    0

    Least Privilege Tool Access for Agents

    by Zé Figueiredo

    $12

    Give autonomous agents read-only tools by default and unlock each side-effecting tool only after it's individually tested and approved, so permissions reflect what's actually verified safe.

    1
    0

    Eval Gated Deployment

    by Zé Figueiredo

    $15

    A deploy gate that blocks shipping an agent change if it regresses on a hand-written evaluation set, with per-call cost tracked alongside accuracy.

    2
    0

    Human Approval Gate

    by Zé Figueiredo

    Free

    A production-tested pattern for pausing an autonomous agent before irreversible actions, with SLA timeouts and a safe automatic fallback.

    1
    0