FiredogDaily 1.0 out soon!Click here to learn more.
Product

Firedog Daily

Firedog reads your provider usage and your gateway logs. It never sits in the request path, so it cannot slow down or break a workflow in production. What comes out is not a dashboard. It is data a leadership team can act on.

STEP 01

Connect your AI stack

Read-only keys for OpenAI, Anthropic, Azure OpenAI, Bedrock, and your internal services. Fifteen minutes, no code in the request path.

STEP 02

Attribute every request

Every prompt, model, user, and workflow is tracked automatically, and tagged with a team and an owner. Including the calls nobody wrote on purpose.

STEP 03

Understand your spend

Cost per run, per user, per team, per workflow. The unit economics of every AI decision, before the invoice arrives.

The invoice arrives after the decision. Firedog closes the loop between the request and the invoice line, so leadership decides with the same number engineering can open and inspect.
6
cost components tracked
13
workflows modelled
50-73%
unattributed share observed
0
bytes of prompt content stored
Method: every figure on this site is computed from published provider rates and documented workflow structures, not from client data. We publish the structure, never a number we did not measure.
Use cases

Built for AI workflows that matter.

Thirteen workflows companies already run, across sales, operations, HR, engineering, research and compliance. Each one is decomposed to the cent, and each one hides most of its cost.

Research

Earnings call analysis with RAG

Ingest 50-200 transcripts per cycle, run analyst Q&A against them with context stitched from a vector index.

per run$1.14
per year$68k
unattributed73%
Research

Market research synthesis (agentic loop)

Multi-source research agent that autonomously browses, retrieves, and synthesizes a structured sector brief.

per run$5.51
per year$83k
unattributed51%
Compliance

Regulatory filing review

10-K, prospectus, and fund-doc review using a long-context model to extract risk factors, covenants, and material changes.

per run$0.84
per year$13k
unattributed62%
Research

Portfolio monitoring and signal generation

Recurring agentic run across multiple tickers - news, filings, macro data - producing structured trade signals with compounding history.

per run$0.65
per year$16k
unattributed64%
Research

Deal and investment memo generation

Structured investment memo from 20-50 source documents - CIM, financials, management decks, diligence notes - with citation-backed sections.

per run$5.45
per year$25k
unattributed58%
Operations

News and filing alert triage

High-frequency classification and summarization of news and SEC filings into structured alerts routed by materiality tier.

per run$0.021
per year$21k
unattributed61%
Compliance

Counterparty and KYC document review

Bulk ingestion of counterparty packs, ownership structures, and AML docs with redundant retrieval patterns typical of compliance workflows.

per run$0.82
per year$6.6k
unattributed69%
Knowledge

Internal research chatbot over fund knowledge base

Analyst chat interface over a RAG index of internal research notes, models, and meeting transcripts with multi-turn conversation history.

per run$0.69
per year$43k
unattributed66%
Sales

Sales proposal and RFP response generation

Draft a branded, on-message commercial proposal from Salesforce opportunity data and a Box library of past decks, with citation-backed sections.

per run$0.77
per year$15k
unattributed50%
Operations

Meeting summarization and action-item routing

Turn Zoom, Google Meet, and Teams transcripts into structured summaries and route action items into Slack and Salesforce automatically.

per run$0.063
per year$8.4k
unattributed50%
HR

HR and benefits helpdesk chatbot

Employee-facing chat over Workday data and policy docs, answering PTO, benefits, payroll, and policy questions inside Slack or Teams with multi-turn memory.

per run$0.58
per year$13k
unattributed67%
Sales

CRM hygiene and opportunity enrichment agent

A scheduled agent that reads meeting notes, emails, and market data, then updates Salesforce opportunities - filling fields, advancing stages, and flagging stale deals.

per run$0.53
per year$13k
unattributed59%
Engineering

Agentic coding assistant for engineers

An in-IDE and CI coding agent that reads the repo, writes and edits code, runs tests, and opens PRs - iterating until the task is green.

per run$1.35
per year$68k
unattributed57%
Method: token volumes are modelled from documented workflow structures and priced at published provider rates, July 2026. These are not client figures. Your first report uses your own workflows.
How it works

Three steps. Under ten minutes.

01

Base-URL swap

Change one line in your OpenAI, Anthropic or Azure client. The collector becomes a transparent proxy.

02

The collector measures

Every call is priced, recorded, tied to a workflow. Prompts and responses stay in your VPC.

03

Five views that decide

Cost, performance, ROI per workflow, per team, per organisation. Drill down to the CallRecord.

What Firedog measures

Every source of AI spend.

01

Models

Compare model costs across providers on the same workload.

02

Prompts

Understand how prompt size contributes to cost, run after run.

03

Workflow execution

Trace every API call from start to finish. Routers, retries, reflection steps: real billed calls hidden inside one logical invocation.

Invisible on your invoice
04

Retrieval

Measure embeddings, reranking and vector search costs, usually billed by two other vendors.

Invisible on your invoice
05

Context growth

Spot conversations that quietly become more expensive over time. An agent pays for its own transcript again on every turn.

Invisible on your invoice
06

Connectors

Box, Salesforce, Slack, Zoom. Every sync is a billed model call, logged as a pipeline step, never as workflow cost.

Invisible on your invoice
Comparison

Most tools stop at the invoice. Firedog explains it.

CapabilityCloud dashboardsFinOpsFiredog
Workflow-level attribution--Yes
Prompt-level visibility--Yes
Orchestration and retry cost--Yes
Context growth over time--Yes
Model comparisonAggregatePartialYes
Leadership + engineering, one view-AggregateYes
Internal tools sit between the two: partial on attribution, rare on a shared view.
Objections & questions

What procurement will ask.

Where do my prompts and responses live?

In your VPC. Prompts, RAG context and responses are written to a local Postgres you control. Firedog receives only metadata — never content.

GDPR and data residency?

Control plane hosted in Europe. Any personal data stays in your data plane. DPA available on request.

SOC 2?

Type I in preparation. The architecture (metadata-only on the Firedog side) sharply reduces the scope.

Which LLM providers?

OpenAI, Anthropic, Azure OpenAI, Mistral, Bedrock. Any OpenAI-compatible API via base-URL swap.

Migration and rollback?

One line of code to change, one line to revert. Zero lock-in.

Commitment?

Monthly. Cancelable anytime.