02
Use cases

Deep where it counts.

One system, three configurations. The agents differ, the jobs differ, the boundary differs — the record layer underneath is the same one, and it ships with all of them. They are staged, not parallel: aviation security leads, and each panel below says exactly where it stands. We are looking for one design partner per industry. What follows is the design and the limit, not client results.

>40%
of agentic AI projects will be canceled by end-2027, Gartner predicts — costs, unclear value, weak risk controls. The reason Manifest exists.
Gartner · Jun 2025
62% → 23%
of organisations are experimenting with AI agents — but only 23% have scaled one. The gap is operational, not technical.
McKinsey · Nov 2025
80%
of common customer-service issues resolved autonomously by 2029, Gartner predicts — at ~30% lower operating cost.
Gartner · Mar 2025

Analyst and field research on agent systems at large; predictions are labeled as such. None of it is a Khelion result — ours go to the Lab when they are real.

Manifest for aviation security

Operator compliance · deployment codename Airside

Screening is already a human-supervised detection system, and the machine is the part that works. What fails is everything around it: background checks that must be reviewed continuously or repeated every twelve months for every pass holder, recertification windows that drift, competency that degrades unnoticed between audits, a security programme that has to absorb every new regulation, an inspection file assembled in panic. Manifest holds that perimeter and never touches the screening decision.

€981.7M
raised by France's airport tax in 2016 — the main funding line for airport security, already running a deficit then.
Sénat · 2016
4,000+
unfilled airport jobs in Paris alone in spring 2022 — with screening named the critical shortage by ADP's chief executive.
Reuters · 2022
01/01/2028
occurrence reporting becomes mandatory in every EU Member State — classification, analysis, confidential channel included.
Reg. (EU) 2026/247

Competency drift

Reads the Threat Image Projection results the operator already has to keep. Week 33: 1,284 projections across six lanes; the night shift on lane C falls from 87.1% to 79.8% over six weeks — a −2.4σ drift that monthly averages hide. A targeted plan goes to the supervisor. It never writes into the TIP system, and a TIP score is never a sanction.

Credentials and passes

Holds the whole population of pass holders against the rule that applies: background check reviewed continuously or repeated inside twelve months, pass valid five years at most, withdrawal immediate on failure or non-return. Shows what lapses next and prepares the file. A person with authority decides about a person.

Training and recertification

Tracks every recertification window and recurrent-training date against rest and rotation limits, and flags the week-38 clash seventeen days before it becomes a finding. It delivers no approved training and certifies nobody — that belongs to the authority.

Regulation into your programme

Each new implementing regulation is compared clause by clause against your own security programme: what changed, who owns it, by when, and the draft amendment. Built to work without classified material — that stays with the cleared human.

Inspection and corrective actions

An evidence pack that is always current, findings tracked to their corrective action plan and closure, every claim linked to the record behind it. It refuses to produce evidence it cannot source.

Why now — 1 January 2028

Occurrence reporting becomes mandatory

Commission Regulation (EU) 2026/247 of 2 February 2026 replaces Annex II of Regulation (EC) 300/2008. From 1 January 2028 every Member State must run a process for reporting, classifying, processing, storing, protecting, analysing and aggregating aviation security occurrences, with a confidential channel and a common classification. It creates a job most operators do not have yet.

BuyerHead of aviation security · quality and compliance manager · operations director of a screening contractor
Judged onCredentials caught before they lapse · recurrent-training compliance · findings per inspection · time to close a corrective action
BoundaryNever touches a screening decision. Never interfaces with certified detection equipment. Never writes into the TIP system. Never scores an individual for insider risk. Never contacts staff directly.
DataStaff data pseudonymised at ingestion, processed inside the operator's environment where required. Classified material stays outside the system by design.
airside · mission — a new regulation lands at 06:12closed 07:42
06:12watch.journal new implementing regulation published · 214 clauses readdone
06:13compare.programme your security programme compared clause by clausedone
06:14compare.programme 3 clauses affected · §4.2.1 · §11.3 · §19signal
06:15draft.amendment amendment written for §4.2.1 and §11.3 · each line sourceddrafted
06:15check.sources §19 has no owner in your org chart · will not invent oneheld
06:16warrant.R12 attempt to file with the authority → refused, needs a signatureblocked
06:16route.human packet to the Quality Manager · 3 clauses, 1 unresolvedhuman
07:41human 2 approved · §19 returned with an owner namedsigned
07:42draft.amendment final text written and filed · logged led_48501closed
Publication → filed amendment1 h 30
draft → supervisor (excerpt)unsigned
To: Head of Screening Ops
Re: Lane C night cohort — retraining proposal (W34)

Detection on partially occluded categories fell
from 87.1% to 79.8% over six weeks (n=1,284).
Two 45-min refreshers proposed, off-peak, W34.
Sources: led_48188 · led_48194 · led_48201

[ Draft — requires review and signature ]

Manifest for medical devices

The regulatory file, produced by agents · codename Continuum

A device manufacturer owes the authorities a stack of documents that never stops: periodic safety update reports, post-market surveillance reports, clinical follow-up literature reviews, trend analyses. The work is multi-source assembly with citation discipline — read everything, attribute every claim, write it so a notified body cannot knock it down. It is exactly what an agent system does well and exactly what a human has to sign. So we sell the signed file, not software for your quality system.

4 months
a year is what 70% of manufacturers need just to update their post-market surveillance reports.
MedTech Europe · 2024 survey
86 / 91%
of large manufacturers and SMEs cannot recruit the qualified regulatory staff they need.
MedTech Europe · Mar 2025
59.1%
of the medical-device regulatory affairs market is already outsourced — the buying route exists, we do not have to invent it.
Grand View · Dec 2024

PSUR and PMS reports

One device family, one report, one fixed price. Agents pull complaint data, vigilance records, registry and literature sources, and draft to the structure the notified body expects. Every sentence carries its source. A regulatory professional reviews and signs. We are contracting that signature rather than pretending to hold it: today it comes from a named partner, disclosed to you before you sign anything.

Article 88 trend analysis, defensible

The regulation makes you predefine the method and the observation period. Most companies do it in an unvalidated spreadsheet, and notified bodies attack exactly there: undocumented competence, unvalidated calculation, method misapplied. We deliver the method dossier — chosen method justified, thresholds argued, calculation reproducible and versioned, refreshed each quarter.

PMCF literature review

The search protocol, the screening log, the appraisal, the write-up. Reproducible: run the same protocol next year and the delta is visible instead of being re-litigated from memory.

Complaint backlog, cleared

A one-off engagement on a backlog that has grown past manual triage: normalise the intake, de-duplicate, code, cluster and order the queue with every decision traceable. The algorithm orders the queue. It never decides what belongs in it.

Why this shape, honestly

We are deliberately not selling you software

Putting a tool inside your quality system triggers software validation on your budget, a supplier quality agreement, an audit right, and a procurement grid that a young company fails on financial-stability criteria alone. AI-native vendors already sit in that seat and we are not going to out-muscle them there. A signed deliverable is a purchase order — and it puts our work where it can be judged: on the file itself.

BuyerDirector or senior manager, post-market surveillance · regulatory affairs manager · the PRRC of a manufacturer small enough to outsource that role
Judged onInternal hours per report against your own last cycle · notified-body questions per submission · time from data cut-off to signed file
BoundaryWe produce documents and analysis. We do not decide reportability, we do not sign in your place, and we do not install anything inside your quality system.
StatusIn build. We are looking for one manufacturer willing to benchmark us against their own last reporting cycle — that measurement is the point.
continuum · mission — a PSUR, from data cut-off to signatureawaiting signature
D+0read.sources complaint export, vigilance records, registry and literature pulled · 4 sources reconcileddone
D+1model.trend method applied per the plan written last quarter · thresholds unchangeddone
D+1model.trend one lot crosses the predefined threshold · flagged for the risk filesignal
D+2draft.psur written to the expected structure · 214 claims, 214 sourcesdrafted
D+2check.sources 3 claims cannot be traced to a record · removed, not softenedheld
D+3warrant.M02 attempt to state a reportability conclusion → refused, that is a human callblocked
D+4route.human to the regulatory professional who signs · with the open questions listed firsthuman
Claims in the file without a source0
article 88 — the method dossierdocumented
# written before the data, not after
series:      complaints / 10k exposure-days, by lot
method:      CUSUM + Bayesian change point · 2 of 2 agree
period:      quarterly, justified in writing
competence:  named reviewer, qualification on file
validation:  calculation versioned and reproducible

flagged:     lot L-2291 · day-3 removals +38%
not_flagged: 6 apparent spikes — matched to a sales
             campaign, not to the device

Manifest for insurance operations

The document back office · codename Binder

A wholesale broker receives statements, membership files and claim documents from hundreds of partner offices, in as many formats as there are senders. Somebody re-keys them. That re-keying is the cost line — not underwriting, not pricing, not advice. Manifest turns incoming documents into checked, structured data in the system of record, and stops at every point where a human has to decide.

18.8%
of premiums go to management costs in French health cover — €8.8bn a year, which the Senate has called scandalously high.
DREES · Dec 2025
7.44M
motor claims paid in France in 2024, for €17.7bn — in a line running at a 100.3% combined ratio.
France Assureurs · 2024
~50%
of 550,000 emails a year handled by agentic AI at one European insurer — a vendor-published figure, and the only named one we found.
Guidewire · Nov 2025

Statements, one schema out

Forty formats in, one checked file out, every morning. Amounts reconciled against the contracts, missing lines named rather than guessed, discrepancies raised with the partner office that sent them. The unit is a file processed, and you can count it.

Membership and enrolment intake

Incoming enrolment files read, required documents checked off, what is missing requested automatically with the right reference. The handler opens a complete file instead of building one.

Claim correspondence

Inbound mail sorted by what it actually asks for, attached to the right file, prepared for the handler. Anything touching a refusal, a liability question or a vulnerable customer stops and waits for a person.

Delegated-authority reporting

If you manage business on someone else's paper, you owe them a report in their format on their schedule. Supervisors have said plainly that these reports arrive inconsistently. We produce yours from the work itself, not from a quarter-end scramble.

What we removed after the market study

Two things we no longer sell here

We had planned a third-party register for European operational-resilience rules and an AI inventory. The register does not apply to insurance intermediaries below 250 staff and €50m — most brokers are legally out of scope, and selling it would have meant selling an obligation they do not have. The AI inventory matters, but from December 2027 and to insurers, not to brokers today. Both dropped.

BuyerManaging director or operations director of a wholesale broker or managing general agent, 30–300 staff · production director of a delegated manager paid per file
Judged onFiles processed per person per day · re-keying hours removed · discrepancies caught before settlement · time to a complete file
BoundaryIt gives no advice, recommends no product, accepts or refuses no claim, and never contacts an insured. It moves documents, not decisions — which is also what keeps it outside regulated intermediation.
StatusExploration. It opens properly once aviation security is proven — we would rather say that than pretend three run at once.
binder · mission — the morning statement runnominal
06:40read.inbox 38 statements from 31 partner offices · 12 distinct formatsdone
06:44normalise mapped to one schema · 4 218 linesdone
06:46reconcile matched against contracts · 27 lines do not tie outsignal
06:47check.gaps 9 lines missing a policy reference · listed, not inventedheld
06:48warrant.B03 attempt to write to the accounting ledger → refusedblocked
06:50draft.queries 3 partner offices queried · drafts prepared, unsenthuman
08:05human queries sent · file loaded · 1 h 25 before the team arrivesclosed
Lines written without a source document0
what the run replacedbaseline
# measured on your own team, before we start
today:    2 people · 3 h each morning · re-keying
errors:   caught at settlement, not at intake
after:    one reviewed file at 06:50, exceptions only

we_charge: on files processed, not on seats
# if the count does not move, neither does the price
Not one of these three?

Most of the work worth automating is specific to one company and appears in no catalogue. We take one process you already measure and engineer the system around it. That is the bespoke route, and it is at the bottom of this page.

Describe your process →

Your own process.

Most of the work that exhausts a team is specific to that team: a reconciliation nobody outside the company would recognise, a dossier assembled from six systems, a watch someone runs by hand every Monday. No vendor sells that. We build it, with Manifest underneath from day one.

Two weeks inside the process

Not a workshop. We watch the real work: what gets opened, what gets copied, where the judgement happens, what the person is afraid of getting wrong. Those two weeks are the paid scoping.

The warrant before the agent

What it may do, what it may never do, when it stops and asks. Agreed in writing at this point, not discovered in production.

Built on your own past cases

Including the awkward ones. If it cannot beat your current process on those, we say so and stop.

You keep the parts

Warrant, evaluation set and log are yours from day one. Handover of the configuration is a fixed fee, agreed at signature.

How it is priced

A paid scoping fortnight, deducted in full from the build. The build is quoted after scoping, in writing — and the quote holds. Manifest is included from day one: we do not ship an agent we cannot account for.

diagnostic output — the brief (excerpt)week 1
# what the week produced
process:     "weekly supplier-risk review"
owner:       "Head of Procurement"
today:       6.5 h/week, 2 people, 3 systems
judged_on:   suppliers flagged before an incident
today's_score: 4 of 11 caught in the last 12 months

autonomy:    act_on_approval
human_gate:  any contact outside the company
kill_rule:   below 8 of 11 at month 3, we stop and
              refund the last month

verdict:     build it  # the other verdict exists
The other verdict

Sometimes the answer is a spreadsheet

Some weeks end with “you do not need an agent here — here is the two-day fix instead”. You keep the written brief either way. Charging for the week is what lets us say it.

Programme panels illustrate the design, the boundary and the reporting format. No client has run these yet; they are not client results. Real numbers go in the Lab once they are real.