Free tools for the agent economy
Interactive tools to assess and test your AI agent's spending. No signup, no install.
By the sipi.bot engineering team · Published 2026-07-13 · Last updated 2026-07-17
Agent Spend Risk Calculator →
Input your agent's spending pattern and get a personalized risk score, worst-case cost projection, and recommended guardrail rules. Free, runs in your browser.
Firewall Playground →
Test the real sipi.bot firewall live. Enter a transaction and see APPROVED, BLOCKED, or FLAGGED instantly. No API key needed.
Why these tools are free
Both tools answer the two questions every team asks before putting a spend firewall in front of an autonomous agent. The risk calculator answers "how bad could it get?" — it takes your average transaction size, transaction rate, agent count, and monthly budget, and projects what a runaway retry loop or an unsupervised overnight session could cost. It runs entirely in your browser; nothing you type is sent to a server.
The playground answers "what would the firewall actually do?" — it sends your test transaction to the same production /v1/transactions/evaluate endpoint that paying customers call, and shows the real APPROVED, BLOCKED, or FLAGGED decision with the rule that produced it. The engine behind that endpoint is deterministic and passes a public eval suite of 53 labeled spend scenarios (53/53).
When you're ready to wire the firewall into your own stack, the framework integrations cover LangChain, CrewAI, the OpenAI Agents SDK, and the Vercel AI SDK with a client of just a few lines, the core is MIT-licensed and free to self-host on your own hardware, and the hosted service is a flat $99/month with no per-call fees and no metering.
Why Tools matters for agent spend control
Whether you are exploring tools, comparing solutions, or evaluating specific features, the central challenge remains the same: autonomous AI agents can initiate financial transactions, and without real-time enforcement, those transactions can escape human oversight in milliseconds. A policy that is not enforced before the transaction executes is not a control — it is a hope.
Pre-spend enforcement can stop a policy-violating transaction before the payment call; incident reduction depends on the policy and integration. The mechanism is straightforward: every transaction runs through a policy check that returns one of three decisions, and the agent acts on that decision before the money moves. No dashboard-watching, no after-the-fact reconciliation, no "we caught it on the next billing cycle."
Key considerations for tools
- Enforcement vs. observation: Dashboards tell you what happened. A spend firewall stops what should not happen. Both are useful; they are not substitutes. Start with enforcement, add observation for attribution and analytics.
- Per-agent vs. global policies: Different agents have different spend profiles. A research agent and a billing agent need different limits. Configure per-agent policies from day one.
- Velocity limits are non-negotiable: A per-transaction limit will not catch a loop of 200 small calls. A velocity cap (max transactions per minute) is the specific control for the most common runaway pattern.
- Merchant allowlists prevent the worst-case scenario: A compromised agent can be redirected to any destination. An allowlist ensures it can only transact with vendors you have explicitly approved.
Next steps
sipi.bot enforces all four control dimensions — per-transaction limits, daily ceilings, velocity caps, and merchant allowlists — with a deterministic rules check and no model call. Pricing starts at $99/month for unlimited evaluations. Deploy in under an hour: define your policy, wrap your agent's spend functions, and run the three test scenarios (APPROVED, BLOCKED, FLAGGED) before going to production.