Fetching from the wire…
01
02
03
04
05
06
07
08
Public story · 2026-03-02 · source-backed
SaaStr operates with 3 humans and 20+ AI agents. Non-engineer Amelia built a sponsor portal replacement in 1.5 days using Claude Cowork — fed it the existing tool's URL and said "write me a spec for a replacement with AI features baked in." SaaStrSponsors.com now manages millions in sponsor revenue. Their updated 90/10 rule: buy 90% off the shelf, build the 10% — but if a paid tool has zero AI features in 2026, start building the replacement. Most concrete public case study of a company running on agents. SaaStr
Each link below shares sources, entities, or timing with this story.
This is the most complete production-agent build sheet I've seen anyone publish, and almost every number in it argues against how the rest of us are building agents. Replit disclosed the internals of two production agents at SaaStr AI 2026: 10K, an autonomous VP of Marketing,...
A pharma company with a market cap in the hundreds of billions is pulling roughly 80% of its ServiceNow and adjacent app workloads onto an internal platform called Concierge, built with Cursor and Claude Code, targeting about $10M in savings. Matterfact's SaaS recap has the de...
Agent 10K wrote about 1,000 commits and 14,000+ lines, ended a seven-year Notion subscription and migrated off Marketo for "about $14 in compute and an hour of API time." Annie replaced their Squarespace site in 46,000 lines. Amelia handled 402,000 interactions and booked 614...
Jason Lemkin's July 29 piece argues legacy B2B SaaS is dying of neglect rather than AI, using Adobe Marketo as the case: 1.5 days of downtime, a missed send to 450,000+ subscribers, a broken unsubscribe link left live for over two weeks, all on a $60,000 ACV contract that came...
SaaStr's July 21 post argues against the "give agents a Postgres database and let them rip" position with four failure modes: 20+ agents each reinvent business rules without shared logic, downstream billing/BI/marketing need a canonical record, humans still need pipelines and...
Everyone's talking about building agents. Almost nobody's talking about managing them. SaaStr published the most granular operational report I've seen on running a multi-vendor AI agent fleet: 30 agents, 3 humans, across Agentforce, Artisan, Qualified, Monaco, and custom build...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.