Category: Company News

We’re excited to be at the Vancouver Tech Crawl this October 21st, presented by North Bank Innovations! If you’re in Vancouver and curious about what’s new in AI tooling for teams, come find us.

The tech crawl brings together builders, founders, and folks working on real problems. We’ll be there talking about how Swa fits into the workflow—no more tab-switching between ChatGPT, Claude, and Gemini, and no more per-seat pricing that breaks your budget.

Here’s what we’re demoing: Swa routes your question to the right model. Pulls context from your docs, your Jira tickets, your tools – whatever matters for the answer.

A lot of teams are tired of the AI tool sprawl. You want one interface, smart routing, and pricing that doesn’t penalize you for exploring. That’s what we built.

Stop by the crawl and let’s chat. Or if you want the details first, check it out here: https://luma.com/northbankcouvecrawl

See you there.

The short version of our PNSQC 2026 paper. The rest is in Portland on Tuesday, October 13.

Software testing used to be rather simple. Known input, expected output, pass or fail. AI changed that.

What gets less attention is what happens when you go from one model to many.

One application talking to one model provides containment. There is a single place where the answer can vary, and you can put a rubric around it. Swa is not that. A request gets routed to an agent, which calls a model, which calls a tool, which hands its output to another agent… Every hop is a new place to sound confident while being completely wrong.

So here is the failure our tests could not see. A request goes to the wrong agent. The wrong agent answers confidently. Nothing is on fire.

We had thousands of passing unit tests while that was happening. They were never going to catch it. Unit tests prove the code ran.

Two years of working that problem produced four questions, asked in order:

• Did the code execute?
• Did the right agent answer?
• Did it do the “right” thing?
• Was the output any good?

Each one is harder to automate than the one before it, and our own coverage says so plainly: 7,612 tests answer the first question, and 39 assertions answer the second. That is the argument in two numbers. The testing pyramid comes out upside down, automation thick at the base, human judgment heaviest at the top. We stopped pretending we’d automate the top layer away. This is also the premise behind the human-in-the-loop foundation of Swa.

The paper has the rest of the story. What our AI review agent checks on every pull request before a change is allowed to advance. Why the safety layers fail closed. And the half we are still building, starting with assessing judgment at the speed of AI.

Get the paper at PNSQC

“Testing Intelligence: A Journey of Quality for a Multi-Modal AI Orchestration Platform” is being presented at the 44th Pacific Northwest Software Quality Conference in Portland, Oregon. This year’s theme is Quality in the Age of Autonomy.

Our session is Tuesday, October 13. All three of us are presenting it, Mike Sirchuk, Ben Pickett and Rahul Ravel. The conference itself runs October 12 to 14, and the paper publishes in the proceedings.

If you are going, come find us and let’s chat!

-Mike

The platform unifies the top generative AI models into one plug-and-play solution for business.

CAMAS, WA, March 19, 2026 — Swa, a cutting-edge platform specializing in multi-agent generative AI solutions that revolutionize the way businesses operate, today announced its commercial launch. By combining seamless integration with enterprise-grade security and scalability, Swa enables companies to harness the power of generative AI across their tools, data, and workflows, creating a unified ecosystem that simplifies complexity and drives efficiency. As part of its global expansion, the company recently launched a technology center in India to support platform development and provide 24/7 operational support for customers worldwide.

Built for business by business technology leaders, Swa aims to be the “shovel” in the AI gold rush, a foundational tool that businesses can rely on to navigate the rapidly evolving AI landscape. The company’s team and advisor network includes a dozen Nike alumni who helped lead digital transformation efforts at the global brand. Swa provides a stable, adaptable platform that integrates the best tools and models, ensuring businesses can focus on their goals without being bogged down by technical hurdles.

“AI should feel like a utility, accessible to everyone, cost-effective, and secure,” said Mike Sirchuk, Founder and CEO of Swa. “Swa gives businesses a simple way to roll out AI across the organization without forcing employees into a single model, and without sacrificing the controls that security and IT teams need.”

Within the tools teams already use, employees can access and compare outputs from leading models—ChatGPT, Claude, Gemini, Perplexity, Llama, Grok, and more—with additional integrations planned. The platform also supports cross-model workflows that help reduce risk from inaccurate outputs by allowing users to validate and consolidate answers.

“Swa liberates people to focus on the things that only they can do,” says Steven John, Fortune 500 CIO, global business executive, and board member.

Swa is designed to support the needs of all key stakeholders involved in AI adoption. Security and IT teams can reduce shadow AI risk by providing a sanctioned way for employees to use AI tools, while controlling model access, data exposure, and usage limits. Finance leaders gain predictability and cost efficiency through a usage-based model designed to reduce per-seat waste and simplify vendor management. Meanwhile, HR and operations teams can use Swa to answer routine employee questions (e.g., PTO policies, onboarding guidance, expense processes) by connecting approved internal resources directly within their workflow.

“We’ve seen too many organizations get stuck in pilot purgatory, running six-month evaluations while employees work around IT with personal account subscriptions,” said Ben Pickett, COO of Swa. “Swa is built to go from kickoff to company-wide deployment in days, not quarters, because the risk of waiting is higher than the risk of moving.”

Swa is available now for early access to its platform for a limited number of teams. To learn more,visit: www.swa-ai.com. 

ABOUT SWA:

Swa is a plug-and-play AI platform that enables secure, cost-effective company access to leading generative AI models across the workplace productivity tools teams already use. Founded by former Nike engineering leaders and built in Washington, Swa helps businesses eliminate shadow AI, avoid single-model lock-in, and implement enterprise-grade controls for AI usage, governance, and adoption. Learn more at https://swa-ai.com/.