| |
|
| |
Agents that keep working while you sleep
Join AI Tinkerers NYC for a themed demo night on agentic loops: agents that plan, build, verify, & retry without a human in the loop. Not chat wrappers. Systems that run for hours & hand you a result in the morning.
Keynote by Conveo engineer Vincent Vankrunkelsven, author of Nightwatch: how to get your agents to keep working while you sleep. Then a full lineup of community demos on the same theme.
Space is strictly limited & we will be screening attendance.
Apply now for an evening of live demos, real PRs, real failures, & a room full of people building the same thing.
Keynote: Nightwatch, reviewed live
Conveo runs a skill called /nightwatch. An engineer plans a feature in the afternoon, a fleet of agents builds it overnight on a remote box, & one reviewed PR is waiting at breakfast. Every layer is a loop: each worker builds, verifies with a script it can run itself, pushes, & drives its PR until the review agents approve. The orchestrator wakes every 15 minutes, checks progress, & replaces anything that died. The whole thing loops again the next day, with the night's logs feeding the next version of the skill.
For this event, Conveo will kick off a real Nightwatch run the afternoon of October 21, then do the morning review live on stage. You'll see what the fleet actually built overnight: the master PR, the generated test plan, the screenshots, & whatever broke. A recorded run is on standby in case the demo gods disagree.
What you'll take away:
The four capabilities you need to run your own overnight loop: a spawner, a durable message bus, validation agents, & a way to wake a running agent
How to write tickets with a closed verification loop so workers converge instead of drifting
The failure modes that each cost Vincent a night, & the fixes
How the agent mesh keeps messages from getting lost when a laptop closes
Speaker: Vincent Vankrunkelsven, Senior Engineer, Conveo. Joined by Dieter (CEO) & Maarten Claes (CTO).
What is AI Tinkerers?
AI Tinkerers is a meetup exclusively for practitioners with technical, machine learning, & entrepreneurial backgrounds who are actively building & working with foundation models, such as large language models (LLMs) & generative AI. If you're deeply passionate about creating LLM-enabled applications, have hands-on experience in building such systems, & want to connect with like-minded people who share your level of commitment, then this group is the perfect fit for you. With AI Tinkerers meetings happening in many cities, we support a dedicated global community.
Who is this for?
We are not just AI enthusiasts, we are AI Tinkerers. The core essence of AI Tinkerers is active collaboration around early-stage discovery & innovation, which requires a high degree of experimentation, vulnerability, openness to sharing challenges & learnings, & collaboration among individuals with a shared level of expertise.
|
|
|
|
|
|
|
|
