Lance @LKRBuilds

Building agents that obey @ObedienceCorp https://t.co/kkIkcNl7qP fest.build Colorado, USA Joined September 2017

Tweets

565
Followers

750
Following

5K
Likes

27K

Lance @LKRBuilds

15 hours ago

@anchorstack_dev fest.build

1 0 0 12 0

View Details

Lance @LKRBuilds

4 days ago

@BratDotAI Claude code is faster, but when speed doesn’t matter codex is better

1 0 1 34 0

View Details

fest.build reduced my token spend >90% with faster/higher quality outcomes. The key is compounding good decisions, tuning your system so agents make less mistakes over time and relying more on determinism/templating than inference vs relying solely on inference/skills and infinite tokens to eventually fix problems

0 0 1 894 5

View Details

Lance @LKRBuilds

4 days ago

@InderosD @steipete Will add example docs soon, I experience the system as a loop of loops. Requirements/goals come in -> workitems created (intents/designs/festivals) -> fest next loop structures, tracks and executes work -> work completed -> new work discovered -> new requirements/goals created

0 0 1 45 0

View Details

Lance @LKRBuilds

4 days ago

@InderosD @steipete fest.build can help with that

1 0 1 614 5

View Details

Lance @LKRBuilds

4 days ago

@raccoon_azul @patrickc fest.build was built for this. It uses filesystem + git, multiple workflow primitives to create a highly custom workflow designed around your specific strategy/process

0 0 0 34 0

View Details

Lance @LKRBuilds

4 days ago

@patrickc fest.build

0 0 0 29 1

View Details

Lance @LKRBuilds

5 days ago

@petergyang @agents Just use a symlink, tools that use the standard and claude will both update the same file without needing to rely on instructions ln -s CLAUDE.md AGENTS.md

0 0 0 17 0

View Details

Lance @LKRBuilds

5 days ago

@petergyang I create a symlink from AGENTS.md (industry standard) to CLAUDE.md for the memory file and same with skills docs.fest.build/cli-reference/…

0 0 0 37 1

View Details

Lance @LKRBuilds

a week ago

@garrytan The best moat in AI is no moat. Products that restrict user choice aren't going to last in the AI age

0 0 0 13 0

View Details

Lance @LKRBuilds

a week ago

Fest.build was built for this Just in time approach has been core to my festival system since the first, skill like version of the system was published in September 2025. The new version does a much better job enforcing just in time deterministically because agents would often cheat, read everything even when told not to costing tokens and time. The guidance system in the current version solves those problems web.archive.org/web/2026010811…

0 0 0 35 0

View Details

Lance @LKRBuilds

a week ago

Where it's at today, it's focused on a user driving it over months or years. There's 4 workflows built into the system for different scenarios you'd use it, there's structured spec workflow types that live in @workflow/ directory for creating sub directories like design// for simple structured spec types of workflows, intents for capturing rough ideas/notes and festivals for long running complex festival plans. Festivals handle the drift, agents run the festival plans in a fest next loop and it's up to the user to customize the templates used to create the festival plans to add gates and a strategy to prevent drift. The default one works in most cases, but in order for something to truly work for months/years on it's own it needs to be adaptable to the way we're going to be working in 3 to 12 months, and the festival plans are designed around this way. They're like a prompt chain with template based gates. The fest next loop enforces the gates, you can expand upon the default or replace the defaults with your own gates until the system has no drift. I had to simplify the defaults to make the system more user friendly, which also can lead to drift. One way to assist with drift detection is to initialize feedback inside a festival plan with drift detecting criteria, so agents will detect drift on their own and then add a final phase to take that feedback and create a new festival chained to the current one that adjust the run based on the drift that was detected by the agents. In a coding agent session sometimes the agents will just stop following the fest next loop instructions, but you can also just script it to run fest next, and when the agents done create a new session use fest next output as the prompt for that session and continue. That prevents the remaining edge cases not already handled by fest next on it's own

0 0 0 13 0

View Details

Lance @LKRBuilds

a week ago

🚀 Just launched Festival on @trylaunchai! Long term AI workflows over months or years Check it out and show some love 👇 gzpypxgdkxdynovploxn.supabase.co/functions/v1/o…

1 1 1 52 0

View Details

Lance @LKRBuilds

a week ago

@garrytan docs.fest.build/methodology/ca… Festival campaigns are made for this, simple standardized workspaces for all your context, projects and workflows. They’re like organized obsidian vaults with easy cli navigation

0 0 0 10 0

View Details

Lance @LKRBuilds

2 weeks ago

@i_am_brennan @ryancarson In my system, the next step is campaigns to manage all work related to a high level mission that continues until the mission is complete docs.fest.build/methodology/ca…

0 0 0 26 0

View Details

Lance @LKRBuilds

2 weeks ago

@bonsaixbt Fest.build makes this workflow easy

0 0 0 195 0

View Details

Lance @LKRBuilds

2 weeks ago

This is a data problem that can't be solved by AI inference reliably. You can pretend to solve it with inference but eventually the users are going to ask it questions and get a response back that conflicts with their memory and realize it's not useful. The main challenge is making the data collection at the moment it matters natural, if it feels like a chore it adds friction and then doesn't happen