Fresh AI reviewers catch what your drafting assistant can't see

Elephant-Goldfish Model

EGM is an open-source plugin that splits AI-assisted planning into two roles: a drafting assistant that knows your goal, background, and full conversation, and fresh reviewers who start from zero and read only the written plan. They report what's missing or unclear — like a plan that names no staff for the desk or never states the opening hours — and you decide what to fix. The method comes from Dave Rensin's essay on elephants and goldfish in software engineering.

An author knows things that the plan does not say. Reviewers without the conversation find those gaps.
  1. sathish316

    Bitter lesson - anything that can be optimised outside the model or harness will be optimised by the model or harness in the next 2 months.

    After trying any such pattern or skill or next big thing, I keep returning to Peter Steinberger’s advice in 2 weeks and follow “Just talk to it” engineering - https://steipete.me/posts/just-talk-to-it

  2. CharlieDigital

    About 5 weeks ago now, I moved over to Paseo[0] (OSS, Apache 2.0, no affiliation) while trying a few other "meta harnesses".

    This turned out to be a very interesting experiment for me.

    The agent profiles configuration was the most interesting. It looked way too simple. No tools, no real spec, no configuration of skills. But actually, it somehow turned out way more useful/powerful and subtly different from how the native harness models sub-agents.

    I wrote about my setup and why I think it works[1]. The gist of it is that it is effectively a dynamic, multi-agent harness. I know what you're thinking: CC and Codex can do that, too. But Paseo has a few interesting bits: it can use multiple providers, harnesses, and models; the agents can talk to each other or through a coordinator; it has a nice toolset for agents to use and well tuned skills.

    So I have a full team set up and the lead orchestrator then automatically decides when it needs a Member of Technical Staff, a DBA, an End User Advocate, a UI Designer to provide input and feedback.

    As I wrote in my blog post, the main wins I observe are that: 1) the autonomous output is better, higher quality, more detailed because of internal team critique, 2) I can spread my tokens better across OpenAI, Anthropic, and DeepSeek; it may not be overall more "economical", but I can effectively "stretch" my sessions by distributing tokens.

    I recommend checking out https://agentmgmt.dev/ and finding the right meta-harness for you since I […]

  3. sbarre

    I tried EGM on a few things over the last couple of weeks.

    The biggest pitall, which is called out in the docs, is that the goldfish reviewers are never fully satisfied.

    The reviewers will always find something, so you need to be able to recognize when the agent is bikeshedding and that it's time to move on.

    Otherwise it's a pretty decent approach, and while I don't think it's anywhere near hands-off, it produced decent specs in both cases that didn't require too much additional hand-tuning before I started implementation.

More from this day

2026-11-17