You're running Claude Code, Codex, and Cursor in parallel.
You have no idea which one to trust, what it cost, or where it keeps failing.
Worldline v0.1.9 is live: the independent control room for AI agents at work
→ captures local Claude Code + Codex work
→ independently verifies outcomes
→ cost per verified outcome
→ Trust Memory across runs
→ surfaces what needs attention next
The model is interchangeable. Your verified action history isn't.
Download the free Mac App now worldline.chaoscha.in/
Coding agents are quick to say “done.” Figuring out what they actually did can take longer.
Worldline v0.2 brings Claude Code and Codex session history into one place, so you can pick up previous work, review recorded activity and security observations, and see where a tool failed.
Try it: getworldline.com
Your company should own the intelligence its AI work creates.
That’s the thesis behind ChaosChain and Worldline, our governed workspace for human-agent work.
Our new company site brings together the vision, product and open research:
chaoscha.in/
AI agents are doing more work. Keeping track of what they did is becoming a job of its own.
A peek at Worldline’s new multiplayer Control Room for people and agents to share context and hand off work without starting over.
Pro + Team are coming. DM me for an early look.
We’re hiring a Founding GTM Lead in India.
Own 0→1 enterprise and public-sector GTM for Worldline: sales, category marketing, partnerships and paid sovereign-AI design engagements.
Mid to Senior, hands-on, remote.
getworldline.com/careers
We’re hiring the early engineering team building Worldline.
Open roles:
→ Rust Systems Engineer — Desktop, Edge & Security
→ Product Engineer — React/TypeScript, Enterprise Control Room
→ Engineering Interns — Systems or Product
Remote within India.
This is foundational product work across agent capture, independent verification, Fleet, AI security and multiplayer human-agent workflows.
Apply: getworldline.com/careers
Agent work shouldn’t disappear into private sessions.
Worldline is the multiplayer control room for human-agent work: a shared, sovereign operating record of context, actions, evidence, decisions, outcomes and cost across models.
Our new home is live: getworldline.com
ZDR limits what providers retain.
Sovereignty means owning the learning loop:
agent actions, permissions, corrections, failures, verified outcomes and cost inside your boundary and portable across models.
That’s the control plane we’re building with Worldline.
When we look back, Alex Karp may have initiated an important preference cascade around AI sovereignty.
It’s worth noting what @Benioff and @satyanadella are both saying:
Your knowledge, as a company, is your sovereignty. If you lose it to someone else (anyone else) you are hollowing your organization out.
There are many ways to accidentally leak intelligence so you need partners and tools who can sign up for the complexity required to give it to you.
See Benioff below and see Satya’s essay linked below.
This is the right architecture. The compounding loop begins when action data becomes structured evidence: what changed, what was verified, what it cost, which permissions applied, and what the operator decided. Models can rotate; that owned context is what improves routing and governance over time.
The control plane only works if it has evidence.
Enterprises won’t route agent work well just by picking cheaper models per task. They need a trusted record of what each agent did, what context/tools it used, whether the outcome was verified, and what it cost.
The real moat is the governed context graph behind the control plane.
TL;DR: Use a control plane, pick your model on a per task basis, do it massively cheaper as a result, keep your edge, don’t leak it to the frontier labs.
The thoughts below are exactly what we find in large enterprises that use 8090’s Software Factory control plane.
Our control plane is agnostic and sits above all the model chaos. You use it to manage your engineering team. It creates a more rigid conformation to the software development lifecycle so Owners and executives get well documented, governed, auditable software - not broken promises, vaporware pr large T&M bills. Engineers need to do a bit more work upfront but then are relieved of dealing with infinite slop in return.
For example, on a typical migration task of an enterprise workload (PHP—>next.js), when we chose Opus 4.8 inside our control plane, Software Factory gets to the right answer 1.5x faster and 1.4x cheaper than using Opus alone.
If an Enterprise asks our control plane to use an open weight model like GLM, instead, the costs fall even more dramatically. The migration is 16.4x cheaper but 3x slower but still works!
This brings up the obvious: at some near point in the future all large enterprises - ie those currently spending millions per month or more on tokens so they seem brilliant to a Wall Street analyst or their Board - will have to rationalize why the would spend so much more for inefficiency, poorer outcomes and data leakage to providers that increasingly also want to compete with them.
Token burn is the wrong scoreboard.
The metric that matters is cost per verified outcome.
AI spend is about to need the same discipline cloud spend got: attribution, receipts, failure patterns, and cost per verified result.
That’s the layer we’re building at @Worldline_AI
Meta burns $2.65B a year on AI tokens. at $300K for a Meta engineer, that's enough to pay ~9,000 engineers for a full year.
now ask yourself: since the layoffs, has Meta shipped anything that feels like 9,000 engineers’ worth of output?
Agents should not disappear into terminals. They should leave receipts.
Worldline control room is coming together.
One inbox for your agent fleet: what happened, whether the outcome is certified, what it cost, and what needs attention.
8090’s raise is category validation: enterprise software work is becoming agentic.
My view: the next missing layer is independent control: verified outcome receipts, cost per verified outcome, trust memory, and bounded execution across Claude/Codex/Cursor/custom agents.
Every AI software factory needs an evidence layer.
We raised a $135M Series A!
8090’s Series A was led by Salesforce Ventures and joined by WNDR, Craft Ventures, The Production Board, and LAUNCH.
We also had the support of a group of esteemed angels including Nikesh Arora, Cliff Robbins, Adam D’Angelo, Shyam Ravindran, Abhi Arun, and Thomas Laffont.
We’re grateful for their support. It validates 8090’s mission and traction so far, but mostly it accelerates the work ahead.
The capital will go to two places. The first is hiring more people, because the demand we have is accelerating rapidly. The second is investing in the compute and infrastructure needed to keep delivering our solutions at high quality and reliability.
8090 works with the biggest, hardest, most demanding customers in the most regulated industries: healthcare, insurance, life sciences, aerospace, energy, manufacturing, financial services, and the United States government. We help them win by using our AI-enabled Software Factory to design and build entire new systems, refactor old ones, and find and accelerate their edge.
Our view is that as Software Factory is used more and more to do mission-critical work inside industries with the least tolerance for error and the most oversight, it will be used to bring transparency, consistency and control to work everywhere.
And as we expand the potential of the biggest organizations, we are also building a playbook and a series of network effects into Software Factory that will be valuable to everyone, from SMBs to solo founders.
With much gratitude, back to work…
PS - A note on why I am doing this as CEO, rather than from the board.
This is one of those rare moments when the technological ground is moving so ferociously underneath all of us that the decisions made in the next few years will set the stage for the next twenty.
AI can be the grand equalizer. It is the thing that can give everybody a shot, and I would like to help it achieve that potential. Since I left Facebook, I was waiting for a moment like this to return to a full-time operating role. I was a demanding manager back then, but I felt I had no choice given how powerful and undeniable what we were building was. I am convinced that what we are building now is even more important, so there was no decision to make except to be all in.
Model routing is necessary, but for agents the unit of optimization can’t be tokens/request. It has to be verified outcomes.
Cheap model + 4 retries + failed task is not cheap. The applied layer needs evidence from real runs: outcome, cost, reliability, failure patterns, and when to escalate.
At @coinbase our AI spend is down nearly half this quarter while token usage keeps climbing. My team built the infrastructure behind it: routing, caching, cheaper defaults, and the spend services that track it.
We route everything through our own gateway: a single endpoint and format for dozens of models, with cross-provider failover, redaction, logging, and cost controls all applied before anything reaches a vendor.
We started with cheaper defaults and caching. 91% of employees weren't hitting their usage caps. Instead of lowering caps, we set cheaper model defaults to cut spend. Caching took more work to get consistent across every tool and model family. A cache hit needs the prefix to match exactly, so we keep building a long, stable prefix across turns. Each request only pays full rate on the new tokens and reads the rest from cache.
Our routing accounts for caching too. The naive approach scores each turn on its own and sends it to whichever model fits, which seems reasonable but would run up spend. The cache is per-model, so switching mid-conversation invalidates it. Our router weighs cache state alongside how hard the task is: a conversation keeps its model while the cache is warm, and the chance to re-route comes only when it goes quiet long enough for the TTL to lapse. Once it does, the router is free again to pick the best model for the task.
These improvements happened at the gateway, so they apply across every team and tool. Next we're going deeper on the coding harness, where we have the most signal and flexibility, tuning how subagents and context get managed.
Model routing asks: which model is cheapest for this request?
@Worldline_AI asks: which agent instance is most likely to produce a verified outcome at the lowest total cost and risk?