Analyze Allocations With an AI Agent

PlaidCloud’s MCP server exposes your allocation models to AI agents, so once an allocation has run you can ask about its results in plain English from an MCP-connected chat — Claude Code, Claude Desktop, Cursor, ChatGPT, or any MCP-compatible client. The agent reads your allocation model directly, so it already knows how each cost line is built and what drives it.

Note

This runs through an external AI agent connected over MCP, not the in-product AI Assistant tab. See Connect an AI Coding Agent to wire an agent to your workspace, then ask your question in that agent’s chat.

What You Can Ask

Why an Allocation Changed

The most common question — compare two periods and explain the movement:

Why did the revenue-allocated cost line change from January to February?

The agent returns:

• The size of the change — before, after, and the delta.
• What drove it — whether the input cost pool grew or shrank, or the driver mix shifted.
• The top contributors — the accounts, cost centres, or products that moved the most.

Drill Into One Slice

Narrow the same question to a single member to get a precise breakdown:

Explain just the Operations cost centre.

The agent separates the two effects — how much came from the overall pool moving versus the slice’s share of it changing. For example: Operations fell because the pool shrank, even though Operations took a larger share of it.

Where Values Come From, and What They Feed

Trace an allocation’s lineage in either direction:

Where does this cost line come from?

What does the GL cost pool feed downstream?

The agent lists the upstream sources and drivers, or every downstream step the table feeds — across allocations and the transforms between them.

What Drives an Allocation

Is revenue used as a driver, and where?

The agent lists each step that uses the table as a driver — the basis for the split — versus an input, the values being spread.

What a Change Would Do

Ask a forward-looking question:

If revenue rises by 1 million next quarter, which cost lines are affected?

The agent names the affected outputs and an estimated size for each — split across a fan-out by each result’s current share of the pool, so the per-target figures add up rather than each showing the whole change. You can also scope the question to one target — “what would a $1M revenue rise do to Customer A?” — and the estimate is applied to just that slice.

Note

What-if estimates are based on your allocation model’s shares as they stand today. Treat them as a well-scoped estimate of where a change lands, not a precise forecast of a future in which the shares themselves may have moved. If you point a what-if at a driver or basis table rather than the input pool being allocated, the agent declines the estimate and says why — changing a driver reshuffles how the pool is split rather than adding value, so a dollar impact there would mislead.

What Allocations Exist

What cost allocations are in this project?

The agent lists the allocation models and their final output tables — useful for orienting yourself in an unfamiliar model.

Understanding the Answer

Every explanation is labelled with how confident the agent is in it — and, just as importantly, it flags when a confident-sounding number would mislead. Those warnings are carried into the plain-language summary itself, not buried in the detail, so you see them before you act on the figure.

The attribution quality behind the confidence:

• Clean — the change was fully attributed to its drivers. This includes filtered allocations, those scoped to specific accounts: the filter is applied automatically, so the contributors are exactly the rows in scope.
• Partial — the agent can show what changed and where — the totals and top contributors are correct — but cannot fully attribute the why on its own. It tells you why, and what to ask next.

Warnings you may see attached to an answer:

• A year-over-year comparison measured over a still-incomplete current period — or with no prior-year data to compare against, in which case it says there is no baseline rather than calling the change normal.
• A whole-group total that hides a member-level reshuffle underneath it.
• A slice whose factors move together, so the headline percentages aren’t reliable on their own.
• A change whose attributed pieces don’t add back to the reported total.
• A what-if whose per-target impacts can’t simply be summed.

When a result is partial, the guidance usually points you to the slice drill-down above, which gives a real decomposition for a single member.

Current Limitations

Dimension allocations

For allocations driven by a dimension hierarchy — for example, splitting a cost centre across a reporting structure — the agent now explains the change: at the whole-total level it attributes it to the input pool, and when you filter to a specific target it separates how much came from the pool moving versus that target’s share of it shifting. The one thing it can’t yet reconstruct is a precise cause that depends on point-in-time hierarchy history (a later release); the slice drill-down gives the usable breakdown in the meantime.

Cascaded allocations

When one allocation feeds another — a cascade — a project-wide “why” would mix the wrong rows, so the agent asks you to scope the question to a slice, such as a specific region, product, or cost centre, and then explains it.

Results produced by more than one allocation

If a result table is written by several allocation steps, the agent lists the candidates and asks which one to trace — unless you filter to rows that only one of them produced, in which case it traces that step automatically and tells you it did.

Tips

• Name the table and the period. “Why did cost_line_rev change from 2025-01 to 2025-02?” gets a sharper answer than “why did costs change?”.
• Pick a real before and after period with a movement you can sanity-check.
• If the agent analyzes the wrong table, name the project and table explicitly so it doesn’t have to guess.

Next Steps

• Connect an AI Coding Agent — wire an agent to your workspace over MCP
• Allocation results — what the result table contains
• Troubleshooting allocations — when reconciliation fails