We raised $3M on one observation:
Agents learn on your dime. And forget.
Every run, your agent figures out the same APIs, makes the same calls, hits the same failures. Because nothing saved what worked.
We built Rote by @modiqoai to fix this.
Point it at any API. Rote reads the spec and builds a surface your agent can call: auth, endpoints, schemas. That's the adapter.
When your agent finishes a task, Rote saves the exact calls that worked. That's the flow.
Config in. Code out. Runs on your machine. Nothing to watch over.
Agents stop starting from scratch. Teams stop paying for the same work twice.
Install → https://t.co/7clzPnKWwj
Modiqo is attacking one of the least glamorous problems in AI agents: what happens after a workflow finally works once.
The company raised $3M in pre-seed funding co-led by Heavybit and Seligman, with Irregular Expressions participating. Modiqo builds Rote, a local execution layer that captures successful AI-agent runs and turns them into deterministic, reusable workflows.
The production problem is reliability. Agents can complete a task once, then rediscover the same APIs, prompts, scripts, and edge cases the next day. That burns tokens, bloats context, and makes operational behavior harder to audit as models and APIs change.
Rote sits underneath the agent loop. It connects agents to APIs without server infrastructure, sidecars, or SDKs, records what each agent executed, and preserves working paths as durable assets teams can repeat, inspect, and improve.
Quick facts👇
● founders: Chetan Conikee
● total capital raised: $3M Pre-seed
● Investors: Heavybit; Seligman; Irregular Expressions
The interesting test is whether production agent reliability comes from making agents think harder, or from knowing when they should stop thinking and reuse what already worked.
We raised $3M on one observation:
Agents learn on your dime. And forget.
Every run, your agent figures out the same APIs, makes the same calls, hits the same failures. Because nothing saved what worked.
We built Rote by @modiqoai to fix this.
Point it at any API. Rote reads the spec and builds a surface your agent can call: auth, endpoints, schemas. That's the adapter.
When your agent finishes a task, Rote saves the exact calls that worked. That's the flow.
Config in. Code out. Runs on your machine. Nothing to watch over.
Agents stop starting from scratch. Teams stop paying for the same work twice.
Install → https://t.co/7clzPnKWwj
Nick - thanks !
We ship a vault with rote. All of your tokens (static, oauth, etc) and encrypted and stored on your computer. Each adapter has access only to its credentials. If you rotate that you'd have to `rote token set <>` .
We will in the future sync with 1password, lastpass, etc
Rote by @modiqoai tackles the challenge of consistent performance for AI agents by crystallizing agentic actions into deterministic code. Congratulations to @conikeec and the team and welcome!
Congrats to @conikeec and the Modiqo team on the launch of rote. The core idea is practical:
✅ when an agent successfully completes a workflow, capture what happened and turn it into something the team can reuse, inspect, and govern.
✅ getting an agent to work once is not the same as keeping it working after models, APIs, permissions, and business rules change.
🙌 https://t.co/pRnUNpUH22