Fintastic vs Pigment (2026)

Native integrations sync ERP, CRM, HRIS, marketing automation and data warehouse systems into a live actuals version, with no nightly load to wait for, and Fintastic builds a connection for a system it does not yet cover. A Google Sheets add on lets customers pull their own Fintastic data into a sheet through custom functions, signed in with their Fintastic account and refreshed in the background. The agent's work happens inside the planning model those feeds keep current. It reads and builds there, and nothing it does reaches back into the source systems.

Sourcefintastic.ai/integrationsread 2026-10-13

Data reaches the model through scheduled imports from ERP, CRM, HR, data warehouse, BI, spreadsheet and file storage sources, and the agents work on that model instead of inside the source systems. Agent connectors reach outward to Notion and Slack. An admin switches a connector on, each member signs in with their own account, and each read, write or delete tool is set to always allow, needs approval or blocked. Google Drive is still to come, and a team cannot add an MCP server of its own, so agent action outside Pigment stops at those two products.

Sourcekb.pigment.com/docs/set-up-agent-connectorsread 2026-10-13

Each question runs in three parts. The agent works out what is needed, the platform serves only the slice of the model it touches, and the engine computes the answer. Longer work happens over a conversation, such as a planner and the agent shaping a rate curve over fifteen turns on a copy of a version. Fintastic offers no runtime that chains steps, hands work between agents or runs a planning process on its own.

Sourcefintastic.ai/ai-agentread 2026-10-13

In Plan & Build mode the Modeler Agent gathers context, writes a structured action plan and then carries it out across Dimensions, Lists, Metrics, formulas and data imports, asking before it switches to another mode. The Analyst Agent takes a Mission, a task written in plain language, and works through its subtasks.

It sources the data, drills into the drivers, runs its own code against the model's metrics and assembles a report of text and charts. A user can leave an agent working and come back to an unread badge on the chats that have answered. Custom Agents draw on the same analysis and documentation skills, though they cannot schedule Missions.

Sourcekb.pigment.com/docs/configure-and-run-the-modeler-agentread 2026-10-13

The agent starts when a planner asks it something inside Fintastic, whether why a number moved, whether two reports tie, what happens under a change or to build an object. Live actuals arrive continuously through the integrations, yet no schedule, data event or message from another tool starts the agent, and it is not offered in chat tools or outside assistants.

Sourcefintastic.ai/ai-agentread 2026-10-13

Saving an Analyst report as a Mission makes it repeatable, and switching on Scheduling sets a start time and a cadence for later runs, with each run's output kept in the report or exported to a text Metric. The Missions tab shows every saved Mission with its run frequency. People also start the agents from the AI sidebar on any Board, from the AI Analysis button beside a Metric, Table or numeric Widget, and from a prompt typed at the top of the Workspace homepage.

Sourcekb.pigment.com/docs/configure-and-run-the-conversational-analyst-agentread 2026-10-13

The agent queries the live planning model at full granularity, with its dimensions, formulas, versions and dependencies, not an extract or an aggregate a day behind. Structure aware tooling serves it only the part of the model a question touches, so it can trace a figure to transaction lines or read the logic of an existing formula, not its label. Answers stay tied to the same model the plan runs on.

Sourcefintastic.ai/ai-agentread 2026-10-13

Answers come from the customer's live planning model, its Applications, Blocks, Metrics and Boards, and an admin can switch AI data access off on any Block that should stay out of reach. The Analyst prepares itself once per Application on the first question, a setup that takes longer the more Blocks there are.

Custom Agents carry standing knowledge a team supplies, such as process documents, glossaries, FAQs, guidelines and chosen Boards and Metrics, and users can attach spreadsheets, text and images to a chat. When a security admin allows it, the agents also search the web, optionally only on approved domains, and look inside the model first when the answer may be there.

Sourcekb.pigment.com/docs/create-custom-agentsread 2026-10-13

The agent keeps a memory of conclusions and conventions, such as what bookings means in a particular model, while numbers are always looked up fresh. Memories are scoped to the tenant, the version and the user, every one is visible and editable, and the agent changes only memories it wrote, never a person's. Threads stay saved and searchable, one per topic, Board or scenario. How long a memory lasts, short of someone deleting it, is left open.

Sourcefintastic.ai/ai-agentread 2026-10-13

Each member keeps a private chat history with the agents, where chats can be pinned, filtered by Application and reopened to carry on from where they stopped. The Modeler remembers which mode was last used in each chat, and a saved Mission keeps an analysis so it can run again. A team that wants an agent to hold on to its conventions writes them into a Custom Agent's instructions, since chats do not build up a memory of their own.

Sourcekb.pigment.com/docs/pigment-agentsread 2026-10-13

Nothing the agent builds, whether a metric, formula, list, dimension or report, enters the model until the planner approves it, and the agent cannot change the plan on its own. Scenarios run on a copy of a version, so the baseline stays as it was. The agent acts with the asking user's permissions and has no elevated path around the access model, and it can refuse a request the data cannot support and explain why.

Sourcefintastic.ai/ai-agentread 2026-10-13

In Plan & Build mode the Modeler Agent puts its action plan up for validation and waits for a go ahead at each waypoint as it works. Auto accept lets it continue without stopping, except for deletions, which a person confirms every time.

Its changes to the model are permanent and attributed in Application History to the member who ran it, and Ask mode answers without touching anything.

Connector tools set to needs approval make the agent propose a create, edit or delete in Notion or Slack and wait for the member to confirm it, and a web search that might reveal sensitive data asks for approval first.

Sourcekb.pigment.com/docs/configure-and-run-the-modeler-agentread 2026-10-13

Single sign on and identity providers handle login and provisioning, and admins set data visibility by dimension, dataset, view or version for users and groups, inside Fintastic or through third party provisioning tools. The agent runs as the person asking, within the same permissions as a human user down to column level masking, so two people get two correctly scoped answers and no answer carries data the asker could not open. Fintastic holds SOC 2 Type II and ISO 27001 and encrypts data in transit and at rest.

Sourcefintastic.ai/securityread 2026-10-13

Sign in runs through SAML 2.0 single sign on with SCIM provisioning for Okta, Microsoft Entra ID or any compliant identity provider, or through Google Login, with multifactor authentication and domain allowlisting on top.

Group based roles and fine grained data access rights decide who can see and change each piece of data, and the agents, Custom Agents and MCP sessions act only within the rights of the member using them, under separate permissions to use agents and to configure them. Pigment holds ISO 27001 certification and SOC 1 Type 2 and SOC 2 Type 2 reports, audited every year, offers a SOC 3 report, sits at CSA STAR level one and covers GDPR and CCPA.

An independent penetration test summary was refreshed in June 2026, and API keys created since May 2026 follow a structured format that secret scanning tools can catch.

Sourcepigment.com/securityread 2026-10-13

Conversations with the agent stay saved and searchable by topic, Board or scenario, and it shows each object it builds before anything is approved, along with the drivers and postings behind any number it explains. A log of what the agent changed, when and for whom, separate from the conversation itself, is not part of what Fintastic offers today.

Sourcefintastic.ai/ai-agentread 2026-10-13

The Missions tab shows every Mission the agents have run, and each change the Modeler makes is recorded in Application History against the member who ran it, inside edit histories that go down to the block level. Agent outputs explain how they were reached, with the data and logic behind them, and the Modeler writes up each change as it goes. The Audit Trail API sends login, administration, security and application events to a SIEM, and admins follow AI credit use in near real time on the Plan & Usage and AI credits screens.

Sourcekb.pigment.com/docs/pigment-agentsread 2026-10-13

Fintastic runs as a hosted service on AWS with encryption in transit and at rest, continuous monitoring and yearly disaster recovery tests. Which AWS region holds a customer's data, and whether a buyer can choose one, is not public.

Sourcefintastic.ai/platform-overviewread 2026-10-13

Customer data is stored in the region the customer picks, Frankfurt in Germany or Oregon in the United States, on Google Cloud across three independent zones, with backups in multiregional buckets inside the same geography. Buyers who need French or European sovereign hosting can run Pigment on S3NS PREMI3NS, a SecNumCloud 3.2 qualified cloud operated by a Thales subsidiary and shielded from jurisdiction outside Europe. Disaster recovery is rehearsed live once a year against a six hour recovery time and a 24 hour recovery point.

Sourcepigment.com/securityread 2026-10-13

Fintastic offers one AI Agent that works across finance, sales, workforce, marketing and IT plans, and the objects it builds are made to order for each request. Each of those planning areas gets the same agent answering questions about its own plans, from pipeline health and headcount costs to channel efficiency and technology spend. No library of prebuilt agents, planning templates or ready models comes with it.

Sourcefintastic.ai/fpa-softwareread 2026-10-13

The Modeler, Analyst and Documentation Agents come ready to switch on for each Application, and each does its own job. The Modeler builds and maintains models, the Analyst analyzes and reports, and the Documentation Agent answers platform questions from Pigment's knowledge base. Custom Agents come with worked examples for user guidance and for FP&A, workforce and supply chain analysis, and the chat offers a library of suggested prompts. The Analyst comes with ready use cases by role, from monthly expense variance and EBITDA and cash checks to ARR cohorts, hiring gaps and supplier risk.

Sourcekb.pigment.com/docs/pigment-agentsread 2026-10-13

Fintastic does not name the language model behind its agent, and there is no option for a customer to pick or change it. The arithmetic never depends on the model, since the deterministic engine performs every calculation, and customer data and memory are not used to train shared or foundation models.

Sourcefintastic.ai/ai-agentread 2026-10-13

The agents run on pretrained models from AI vendors under enterprise agreements with zero data retention, and customer data is never used to train them. Which vendors and models sit behind the agents is not public, and an admin has no setting to pick or switch the model. Claude, ChatGPT or Mistral can reach Pigment through its MCP server, which puts a team's own assistant in front of Pigment data while Pigment's agents stay on Pigment's choice.

Sourcekb.pigment.com/docs/ai-faqread 2026-10-13

Outside software has no developer route into Fintastic. No API reference, SDK or MCP server is offered for building on the platform or letting another assistant work in the model. The security page mentions encrypted connections to its web services and APIs in passing, and data moves through the native integrations.

Sourcefintastic.ai/securityread 2026-10-13

The public REST API, with a Swagger reference, imports data, exports Metric, Table and List data, returns import configurations and starts data flows, under API keys that carry their owner's access rights, IP allow lists and set rate limits, beside an Audit Logs API.

The Pigment MCP server gives each Workspace its own endpoint and signs people in with their Pigment accounts. Its default tools read and analyze, and advanced mode adds tools that create Applications, build Dimensions, Metrics and Tables, write formulas, design Views and Boards and enter data. Pigment keeps Skills files and plugins for Claude Code and Cursor in a public repository.

Sourcekb.pigment.com/docs/supported-toolsread 2026-10-13

Fintastic suggests buyers judge any planning agent by asking the same question twice, asking something the model cannot answer and asking it to explain a known number. Those are checks a person runs by hand. The product has no test cases, scoring or review step for measuring the agent's answers before or after rollout.

Sourcefintastic.ai/ai-agentread 2026-10-13

A builder previews a Custom Agent and refines it before switching it on for members. Test & Deploy environments stage model changes, the Modeler's included, before they reach a production Application that can be locked, and in managed Applications the Modeler works in Ask mode only. Every answer can be traced to its data and logic. Nothing scores the agents' answers against a test set before rollout.

Sourcekb.pigment.com/docs/create-custom-agentsread 2026-10-13

The agent works through Fintastic's own model, tooling and calculation engine, and data arrives through native integrations, so nothing drives a browser or a desktop application on the customer's behalf.

Sourcefintastic.ai/ai-agentread 2026-10-13

The agents act inside Pigment's own model and reach Notion and Slack through connectors. Web search returns information to them, and none of them opens a browser, drives another application's screen or works a desktop session for a user.

Sourcekb.pigment.com/docs/pigment-agentsread 2026-10-13