Self-Evolving Agents, Self-Improving ROI

Six months ago, most agents completed tasks.

Today, they can remain inside a continuous loop: set a goal → take action → observe the outcome → learn → act again.

Models gave agents intelligence. Tools gave them the ability to act. Goals gave them direction. Loops gave them the ability to improve.

But something critical was still missing: where does an agent’s learning live? How do we know it should be trusted?

That was the challenge behind the Self-Evolving Agents Hackathon in San Francisco: “build an autonomous agent that self-evolves in a continuous loop to achieve a goal — and takes real action. Publish, monitor, orchestrate, or transact, grounded in real sources.”

In 24 hours, 45 teams shipped working agents. Six built on Senso, and the Senso prizes recognized five: SwarmAds, Ratchet, Immune, DeUna, and Greplica.

The strongest projects — in totally different domains — independently discovered the same architecture:

The Senso Loop

How Senso helps developers unlock self-improving ROI

What that buys you:

• Costs fall as usage rises. Every other agent system gets linearly more expensive the more you run it. This one gets cheaper.
• You never pay twice for the same problem. Solved once is solved for every future run — and for every other agent with access.
• The savings are safe to take. Nothing is kept until something proved it worked, so the cheap answer is also the checked one.

Here are some of the winning concepts built on top of the Senso platform. For each one, watch two things: what it decided to keep, and what it stopped paying for.

Ratchet: the cost of intelligence falls with use

Ratchet, built by Aayush Dixit, was the clearest demonstration of self-improving ROI.

Coding agents forget everything between runs, so teams pay to fix the same bug again and again. Ratchet remembers a fix — but only after an independent test proves it worked. Same agent, same bugs, same models. The only variable was memory.

Then Ratchet pointed its memory at a different team’s app — and fixed two of the first four bugs on contact.

The agent didn’t become more intelligent. It stopped paying to think about something it already knew.

DeUna: one answer makes the business permanently smarter

DeUna, built by Axel Cuevas, Anthony Lee, and Andrea Urbina, is a digital twin of a small-business owner who sells through WhatsApp — his voice, his slang, his negotiation style, learned from real conversations.

When something new comes up, the agent doesn’t guess. A customer wanted to trade in a Samsung with a smashed screen; no policy existed, so the agent sent the owner three buttons: Only this one / All the same / Reject.

One tap: “All the same.” The customer got an instant answer in the owner’s voice — and every future customer gets it automatically. No re-ask. No guess. No drift.

The owner configured nothing. He answered one message, and the business became permanently smarter.

Immune: every attack strengthens the defense

Immune, built by Subhan Poudel, applied self-evolution to agent security.

When an agent gets breached by a prompt injection, Immune reads the attack trace and synthesizes a guard rule — an “antibody.” To reach production, the antibody must block the original attack, stop eight mutations of it, and leave twelve legitimate tasks untouched.

In testing, a sixth-generation attack compromised a frontier model 10 out of 10 times. Immune’s antibody blocked it 10 out of 10 times.

From ROI to ROAS

SwarmAds pointed the same loop at advertising: agents generate campaigns, test them in a simulated market, and promote only the winners into reusable memory. The agent learns which actions create revenue and puts future effort there.

Greplica proved the underlying point. Same models. Same task. Different context. Different outcomes.

The next challenge: turn $2,500 into $25,000

A demo is the first step. We want funded businesses. Here’s what’s next for these amazing builders:

Each winning team gets $2,500 in Senso platform credits to keep building with Senso and the Tokens& community — with one goal: demonstrate $25,000 in customer ROI or ROAS by San Francisco Tech Week in October.

Ratchet: cumulative engineering savings. DeUna: recovered sales. Immune: breaches prevented. SwarmAds: measured ROAS lift. Not another demo — proof that self-evolving agents create compounding economic value.

Not at the hackathon? The on-ramp is open.

The same ladder is open to any builder, starting today:

1. Sign up — onboard at docs.senso.ai and get $100 in Senso credits.
2. Prove — turn it into $1,000 of measured ROI or ROAS — against a baseline, not a promise.
3. Payments — that result earns you an interview for a stream of additional credits to expand and grow your customer base with self-improving ROI.
4. Payout — hit $25,000 in customer value and we introduce you to top-tier Silicon Valley investors — with verified results instead of a pitch deck.

Conclusion: the real meaning of self-evolution

The winning projects didn’t retrain models. They built governed memory: successful actions became verified context that could be safely reused.

That distinction matters. Truth is verified, attributable, versioned, and reversible — otherwise “self-evolving” quickly becomes unpredictable and misaligned.

The next generation of agents won’t win on intelligence alone. They’ll win on what they can safely learn, remember, and reuse.

Since September 2024 we’ve run 15+ hackathons in San Francisco with Creators Corner, drawing more than 20,000 developers. We keep the challenge statement deliberately consistent across events — small changes in wording have outsized effects, and adding one word like “self-improving” is enough to move a whole room from static agents to feedback loops.

The wording barely moves. The goal never has: get someone funded. That’s what $2,500 into $25,000 is — the same goal we’ve always had, finally written down as a number, with verified results standing in for the pitch deck.

Start Your Onboarding

Three doors into the loop. Pick the one that matches how you build.

Whichever door you pick, the loop is six commands. Your agent can run them for you:

$ npm install -g @senso-ai/cli
$ senso login
$ senso skills install --all
$ senso ingest <your-domain>
$ senso compile --verify  # the gate
$ senso generate run

Then the loop runs, and keeps running:

Docs & Quickstart →