Stigg 2.0 - The usage runtime for AI products
by•
Stigg is the usage runtime for AI products: the real-time enforcement and governance layer between your app and your billing stack. It decides what every customer, user, team, and agent can do, the moment they try. Millisecond credit checks, zero overdraft, enterprise governance, and modular BYOC. Metering, credits, entitlements, and governance in one runtime. Enforce in the request path instead of reconciling on the invoice. Free forever for AI startups.
Replies
how does the sub-millisecond credit check actually hold up when an agent is hammering the API in tight loops, does it queue or just drop the extra requests
Honestly impressed by how quick the credit checks are - the request path enforcement feels like the right call instead of wrestling with reconciliation after the fact.
how does this handle usage coming from multiple agents or services hitting the same entitlement at the same millisecond without one of them getting blocked unexpectedly
Finally cracked our entitlement sprawl with this. Love that credit checks happen in the request path so we're not patching things together after the invoice fires. Setup was painless.
Congrats on the launch. I hand-rolled entitlements for my own two-plan SaaS last week: one feature flag and a couple of can_use_x? methods (super simple). I assume it ends in tears somewhere around plan number four. Curious where you see the crossover in practice. Is it plan count, team size, or the first customer who asks for a custom contract?
Makes sense, the atomic hold is the answer I was hoping for. The bit I'd still watch is estimate drift: if you reserve worst-case output tokens per call, a 50-wide agent fan-out holds far more than it spends and can start false-blocking once the wallet is mostly reserved rather than actually spent. And a hold from a call that dies mid-stream leaks until something reaps it. Do you release the estimate-minus-actual delta on settle, and is there a TTL on orphaned holds?
usage-based billing for AI products is such a pain to build in-house, we ended up hand rolling half of this ourselves last time and it was way more fragile than it should've been. the BYOC split for governance vs the centralized credits engine is a smart way to keep control without giving up the annoying plumbing
The quiet dread of a customer running up costs way past their plan is very real for anyone shipping AI, so seeing that handled cleanly is reassuring, Dor. Being able to shift pricing without rebuilding everything underneath is the cherry on top.