# SigWise vs. building on an LLM API

Calling an LLM with "is this user a scammer? here are their messages" works
in a notebook. In production, the prompt is the easy part. This page lists
what else you would build, so you can decide whether it is worth it.

## What you would build

| Piece | Doing it yourself | In SigWise |
|---|---|---|
| **Event storage** | A table of events per user, with retention and limits | `POST /v1/objects/{id}/events`. See [Ingesting events](https://sigwise.ai/docs/guides/ingesting-events.md). |
| **History that fits a context window** | Truncation or summarization of long histories, kept up to date | Recent events plus a rolling summary of everything before |
| **Debouncing** | Coalesce a burst of messages into one call, or pay per message | Built in: events a few seconds apart share one analysis |
| **Typed, reliable outputs** | JSON schemas, parsing, retries on malformed output, calibrated probabilities | Three typed [signal](https://sigwise.ai/docs/guide/signals.md) shapes with probabilities and confidence |
| **Changing questions** | Prompt changes, deploys, and re-running old users | Edit a signal with one call; [backfill](https://sigwise.ai/docs/guides/backfills.md) existing objects |
| **Queues and priorities** | Workers, rate limits, and keeping bulk re-runs from delaying live traffic | Live traffic is served ahead of bulk work |
| **Inline checks** | A synchronous path with its own timeouts | `"wait": true`. See [Direct moderation](https://sigwise.ai/docs/guides/moderation.md). |
| **Querying answers** | Store answers, index them, write a query layer | `GET /v1/objects?q=is_scammer >= 90`. See [Search](https://sigwise.ai/docs/guides/queries.md). |
| **Notifications** | Webhooks with signing, retries and a dead-letter queue; Slack and email alerts that don't repeat | [Webhooks](https://sigwise.ai/docs/guides/webhooks.md) and [rules](https://sigwise.ai/docs/guides/rules.md) |
| **Cost tracking** | Token accounting per feature and per customer | Usage by day, model, signal and source. See [Billing](https://sigwise.ai/docs/guides/billing.md). |
| **Console** | An internal tool to inspect users and answers | Included |

## When building it yourself makes sense

- You need a model or deployment SigWise doesn't offer, such as a model you
  host on your own hardware.
- Scoring users is your core product and you want to own every part of it.
- Your volume is large enough that a dedicated team is cheaper than any
  per-analysis price.

## When SigWise makes sense

- You want answers this week, not a quarter from now.
- Trust and safety, fraud or lead scoring supports your product rather than
  being the product.
- You want non-engineers to change the questions without a deploy.

Analyses are billed at their model cost, with no subscription or minimum, so
the comparison is mostly about engineering time. See
[Billing and usage](https://sigwise.ai/docs/guides/billing.md).

## Try it

Every new account starts with $5 of free credit. The
[Quickstart](https://sigwise.ai/docs/guide/quickstart.md) takes about five minutes.