RightCapital

The established platform reading applies, and unusually the vendor's own architectural statement is the clearest evidence for it. A calculation engine covering retirement projection, tax aware distribution modelling and the rest was the entire product from 2015 and remains so, with both inference capabilities arriving in 2026.

The company then states that every agent output originates from that engine rather than from external sources, which is an admirable control and is also a description of where the substance lives: the engine computes and the agent surfaces. Remove the models and advisers build plans exactly as they did through 2025, with more typing. Document extraction in the import capability does carry real throughput, and it feeds a platform that was complete without it rather than one that goes empty in its absence.

Two real controls are published and the third that would earn the top grade is absent. The first is scope: the agent reviews, surfaces and simulates rather than sending, filing or transacting, so the exposure is a wrong conclusion rather than a wrong action, and that is a design choice worth crediting rather than a limitation.

The second is governance of access, since a firm decides at organisational level which advisers and assistants may use the agent at all, which is a supervision lever most vendors in this pocket do not offer. Held below the top grade because searched for any review step between an agent surfaced anomaly or proposed strategy and its arrival in a plan a client will see, any record distinguishing an adviser's own assumption from one the agent proposed, and any audit trail of what the agent did, and located none.

A published architectural constraint addresses the exact failure mode a planning agent has, and that is rare enough to carry this grade on its own. The company states that all agent outputs originate from its own calculation engine, so the agent surfaces figures the verified engine computed rather than producing them itself.

Applied to a product whose answers are retirement probabilities and tax outcomes, that is a structural defence against a fabricated number reaching a client plan, and it is specific and checkable rather than a policy assertion. Held below the top grade because the constraint covers where figures come from and nothing else is measured: searched for an extraction accuracy rate for the import capability, any evaluation of whether the anomaly detection finds what it should or flags what it should not, a benchmark, a validation method or a revalidation cadence, and located none.

An independent research citation is present and it is a placement rather than a measurement, which is what separates this from the top grade awarded twice elsewhere in this session. The company cites a named productivity study by a widely followed independent research house for the claim that it holds the highest user satisfaction among advisers, and names the study and its year, which is more disciplined than the usual unsourced superlative.

Against that, the citation dates from 2024, it reports a ranking without a published figure, and independent survey data from 2026 covering nearly three thousand advisory firms places two competing planning platforms ahead on market share with this vendor's own share unstated in the material located. The one quantified operational figure, a reduction in manual data entry of at least 70 percent, is self reported with no named firm behind it.

Searched for any statement on whether client profiles, uploaded documents or generated plan content are retained, used to improve the service, or used to train, tune or evaluate any model, and located none in either direction. One published statement invites the wrong conclusion and the distinction is worth drawing plainly: the company says insights come exclusively from its own verified engine rather than external sources, which describes where answers come from and says nothing whatever about where client data goes. A reader scanning quickly could take it as an assurance that nothing leaves the platform, and it is not that.

Recorded as an unverified absence. Searched for a retention schedule, a deletion commitment, published processing terms, or any account of how uploaded client documents are handled once their contents have been translated into plan inputs, and located none in the material opened.

That last question is specific to what shipped this year: a document read by the import capability has served its purpose the moment its figures land in the plan, and whether the source file persists afterwards is exactly the kind of thing a firm needs to know and nothing states. Queued check: a privacy policy and processing terms.

Recorded as an unverified absence. Searched the launch material, product pages and trade coverage for a named attestation, an information security standard, an audit report or a dedicated trust page, and located none, and no security page was reached.

For a platform holding complete household financial profiles for thousands of advice firms, and now ingesting uploaded client documents through its import capability, a published position almost certainly exists and was not found in the pages opened. Queued check: a trust or security page.

A software supplier holds no licence and requires none, and no penalty attaches. The output sits close to a regulated act without performing one: a retirement projection and a recommended strategy shape the advice a client receives, and the recommendation is made by the adviser under the firm's own permissions.

Searched for any statement about what a firm must retain to evidence how a plan was constructed, or how a reviewer would distinguish an assumption entered by an adviser from one proposed by the agent, and located none. The second question is the live one, because the agent proposes strategies by varying assumptions and nothing describes how that provenance is recorded.

Searched for any fairness evaluation, any testing of output across client circumstances, or any account of how the agent decides what to raise, and located none. The exposure sits in selection rather than in any explicit judgement about a person.

A review that surfaces anomalies, questionable assumptions and future gaps is choosing which of a household's many imperfections deserve an adviser's attention, and a builder that returns three strategies from a probability target is choosing which three out of a very large space. A consistent tendency in either would steer whole categories of client toward particular retirement ages, spending levels or product choices without any adviser noticing a pattern across their book.

Searched for a warranty, an accuracy commitment, a correction obligation or any allocation of responsibility between vendor and advice firm, and located none. The grounding constraint removes one exposure and leaves the others untouched, which is worth separating carefully: an agent that cannot invent a figure can still miss one.

The check that scans a profile for missing information is the clearest case, because a gap it fails to flag becomes a plan built on incomplete data with an adviser reasonably believing it was checked, and nothing published addresses what the firm may rely on that check to have covered. The client whose plan was reviewed has no described route to see which conclusions came from the agent.

Searched the launch releases, the product material and the trade coverage for a model provider, a model family, a version or an inference host behind the agent, the document extraction or the assistant answering platform questions, and located none.

The same statement noted on the stewardship row applies here and is the reason this record needed care: a claim that outputs originate from the proprietary engine rather than external sources reads at a glance like a declaration that no third party model is involved, and it is a statement about the provenance of answers rather than about the provenance of the reasoning. Nothing published establishes whose model interprets a document or composes an explanation.

Interoperability is evidenced in three different forms and enumerated in none. A named two way relationship exists with a leading meeting assistant vendor, itself indexed here, which is the connection that matters most in this pocket because it closes the loop from a client conversation to a plan input. A migration tool exists for importing from a specific competing planning platform, which is a harder engineering commitment than an ordinary integration.

And the import capability ingests arbitrary uploaded documents, which is interoperability with the world rather than with a system. Held below the top grade because searched for an integration directory naming the client relationship systems, custodians and account aggregators an advice firm runs alongside this, and located none in the material opened, which for a platform of this scale is far more likely an unopened page than an absent capability. Queued check: the integrations page.

Recorded as an unverified absence. The platform is delivered through a browser with a client portal alongside the adviser interface, and nothing about hosting, storage region, tenancy or residency was located in the material opened. Searched for any residency commitment or account of where household financial profiles and uploaded documents are processed and stored, and located none.

The packaging is disclosed and no number is. A buyer learns something genuinely useful, which is that the planning agent carries no incremental charge and is instead gated to the upper two subscription tiers, so the commercial question becomes which tier a firm needs rather than what an artificial intelligence add on costs. That is a clearer answer than most vendors in this pocket give.

Searched for the rate of any tier, a per seat figure or a published comparison of what each tier includes, and located none in the material opened. Queued check: the vendor's pricing page, which this company is generally understood to publish.

A large single profession base in a single jurisdiction, addressed across tiers rather than across institution types. The buyer is a financial advice firm, thousands of them, served through a subscription ladder whose upper tiers carry the agent, so solo practitioners and larger firms are both addressed with different entitlements rather than different products.

Held below the top grade for the reasons that recur throughout this pocket: everything is bound to one country's tax and retirement rules, and no bank, insurer or asset manager is addressed as a buyer in its own right. The migration tool aimed at a competitor's user base is a distribution mechanism rather than a coverage extension.