I just published WAVES, the method I have been using to run AI agents in parallel without letting them run wild. An agent will always tell you the job is done, and WAVES treats that as a claim and checks the evidence behind it before it counts. You fan the work out to a team of agents, each one owns a slice, and the verifier is what decides when the work is done. It runs in Cursor, Codex, Claude, and Droid, and ships as a skill you can install today. The full breakdown is on the blog, with diagrams, the handoff format, and where it fits next to loops and parallel orchestration: https://www.rayfernando.ai/waves-workers-aggregate-verify-extend Skill: https://github.com/RayFernando1337/rayfernando-skills/tree/main#waves--fan-out-to-parallel-agents Give it a run on something real and tell me how it goes.

https://youtu.be/iQyg-KypKAA?is=ADk1EVQNmQ3DKkF-

Not sure if everyone is already doing this, but accidentally stumbled into it and it seems to be working really well. I have told fable to spin up opus or sonnet agents when doing so will not lose intelligence, and it seems to be working really well to reduce costs. --and on a side note, I can't get fable to run a single security audit without downgrading to opus which is really annoying

I have been disappointed with the relaunch of Fable 5 due to the default switching to Opus 4.8. Over the past year I have been using sporadically initially the GLM models from Z.AI within Factory. When Factory added Missions, it was a game changer for me and my process. I am currently testing an alternative that, so far, is working well for me. Here is the stack: 1. 1. Using ZCode as the harness. Z.ai confirmed that this is the best harness for GLM-5.2. 2. 2. I recreated Factory's Mission Skill. I have been super impressed with their Missions workflow. 3. 3. I have a Abacus.AI account that allows me to use their api for different models. This could be replaced with Openrouter. 4. Here is the sauce: In ZCode I added additional custom models (opus-4-8 and gpt-5.5). In the Mission Skill I have three agents: orchestrator (opus-4-8), worker (glm-5.2) and validator (gpt-5.5). The mission skill builds the detailed long running plans in phases and standsup a Mission Control page to track progress. This has been working well for me and giving me great results. The reason why I am all in on ZCode is that I bought a yearly plan last fall and have a ton compute to use monthly. And since the model is now so much better and closer to the frontier models, I finally think it's time for me to fully test it and give it the best harness and structure to be successful. I added a few screenshots. Thanks to @Ray Fernando for the early Factory Droid and GLM exposure last year. 1.

Fable 5 is back you guys and it's included in the subscription until the 7th of July.. After that you have to pay usage credits to use it.