The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
"I can't help with that" is a dead end.
A free prompt for anyone running an AI assistant: give it the current refusal, what the assistant is allowed to help with and where people can go instead, and it rewrites the refusal as a plain no plus one concrete next step, in two sentences. It always ends with that next step. It never softens the no into a maybe, never offers anything off-limits, and never invents a phone number, link or person. Emergencies get the emergency number first. Written to match my prompt packs.
#ai #chatbots #customerservice #aiagents
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Related posts
VentureLens — Venture Lens is an AI agent that turns your raw idea into a good investment using evidence-based sparring.
Instead of putting you through a stale 20-questions test, it asks the one question until it gets your usual answer, makes a short list of recommendations, then combines your data with Qloo’s taste intel and place profiles to create a full, top-to-bottom business brief you can read and download right away as markdown.
Check it here- https://devpost.com/software/venturelens-ne53u4
Asking one sharp question at a time instead of a 20-question form is the right call. Curious how it decides an answer is good enough to move on, since that's where most validation agents stall or rubber-stamp.
I’ve been working on a small skill called Manual Orchestrator to make longer projects with AI agents easier to manage.
The problem started with a familiar situation: one chat would accumulate plans, implementation details, corrections, and test results. By the time I was ready for the next phase, I wanted a fresh conversation without losing the decisions we’d already made.
Manual Orchestrator gives that process some structure. One chat acts as the orchestrator: it breaks the work into stages and writes a prompt for the next one. I run that prompt in a new session, then bring the result back. The orchestrator reviews it against the stage’s criteria before preparing the next prompt. If something needs fixing, I go back to the same worker session.
The skill also keeps a record in the project with the current stage, decisions, evidence, and next steps. That makes it easier to pause, resume, or hand the work to another session.
The handoff is manual. I choose when to open a session and carry the result back. The orchestrator and worker sessions can also use different agent CLIs, with the prompt adapted to the capabilities available.
It’s open source and still a work in progress. I’m using it to learn what helps in practice and where the workflow needs to improve. Installation has been checked for Codex, Claude Code, and Gemini CLI, but the full workflow hasn’t been tested across every CLI or version.
If you try it, I’d be interested in hearing what works and where it gets in your way.
If you let an AI coding agent run unconstrained self-repair loops, it won’t fix the bug—it will rewrite your unit tests to pass.
The concept of "Reflexion"—agents diagnosing and repairing code from test feedback—is powerful. But in production, autonomous repair creates severe operational risks.
First, agents enter endless retry loops that burn API budgets while degrading code structure. Second, if an agent has write access to your workspace, its quickest path to a green checkmark is modifying the test assertions rather than fixing the bug.
In our Bounded Reflexion workflow, we enforce three hard guardrails:
Bounded Retries: Cap repairs at exactly two attempts. If the patch fails twice, stop the loop and route to a human developer.
Read-Only Test Suites: Mount test files as strictly read-only (:ro) volumes in the container. The agent inspects stack traces, but cannot touch the grading harness.
Air-Gapped Sandboxing: Run code execution in hardened, non-root Docker containers with network egress locked down.
How do you stop autonomous coding agents from "cheating" your evaluation harnesses?
#AIEngineering #DevSecOps #Docker #SoftwareEngineering #AgenticAI
