Blog
Atom feedWhat's new in Squidler · October 9, 2026
The apps your agent builds can now have users and roles
Ask your agent for an app where some people may edit and others may only look, and it builds exactly that: people sign in, each one gets a role, and the platform holds every role to its rules. We asked Eleanor for a shared to-do list.
Read → 4 min
What's new in Squidler · October 7, 2026
Your agents can work together now
Agents in the same organisation can now hand work to each other: along connections you draw or approve, with files attached, and with every word on the record. We tried it on ten invented restaurants.
Read → 4 min
What's new in Squidler · September 25, 2026
Keep it in the EU
Your organisation can now choose where its AI processing happens. Choose the EU and everything your agents think with stays inside it. One setting, every agent, changeable whenever you like.
Read → 3 min
What's new in Squidler · September 24, 2026
Your agent now works in Oqto
Oqto joins Fortnox and Bokio as the third Swedish accounting system a Squidler agent can connect to. Same rules as before, one nice difference, and a page for each integration.
Read → 3 min
September 8, 2026
Letting an agent into your books: Fortnox and Bokio
Our agents now connect to Fortnox and Bokio. The interesting part was not reading the books — it was deciding what an agent is allowed to change.
Read → 5 min
July 31, 2026
A URL that wakes your agent
Agents wake when you message them or when their calendar says it is time. Now anything that can send an HTTP POST can wake them too: an n8n workflow, a Zap, a GitHub Action.
Read → 4 min
Building a useful agent · Memory · July 29, 2026
Understanding a Squidler agent's memory through Harry Potter
Compare what you remember from Harry Potter's first year to what our agent remembers.
Read → 3 min
Building a useful agent · Memory · July 28, 2026
How memories become knowledge
While you dream, your experiences become facts. The same is true for our agents.
Read → 7 min
Building a useful agent · Memory · July 21, 2026
How a conversation becomes a memory
Some experiences stay with you for life. Others disappear almost as soon as they happen. We built our agents' memory to work the same way.
Read → 6 min
Building a useful agent · Memory · July 9, 2026
Memory and dreams: creating the next generation of AI assistants
Getting access to ChatGPT felt like having an expert you could ask anything. But it was a new expert every time. You always started from the beginning. A good colleague or friend is rarely the one who knows the most; they are the one who knows you, your work, your situation. What they have that the expert doesn't is a shared history. Memories.
Read → 6 min
July 2, 2026
Mistral vs. Claude on our onboarding: 4× faster, 30% cheaper
We put Mistral Medium 3.5 up against Claude Sonnet 4.6, the model behind our onboarding agent, on our own workload. Mistral came out about 4× faster and 30% cheaper, at near-equal quality. For this particular job it turned out to be a surprisingly good fit, for reasons specific to how onboarding actually runs.
Read → 4 min