Every dose has to be exactly right
Content uniformity, dissolution, weight, hardness, film, appearance: every tablet, every batch, to GMP spec, validated and traceable. The process is unforgiving.
About
The medicine most of the world takes is still made by feel.
Tablets and capsules are taken billions of times a day. Making them is still one of the most craft-bound, reject-heavy, paperwork-bound processes in regulated manufacturing, and the people who hold the craft are retiring. Pildeon exists to capture that craft in a validated system of action and give it back to every plant.
Scenario: Run one immediate-release tablet batch through granulation, compression, coating and inspection inside the approved design space, with QA approval before release. A design walkthrough, not a customer record.
Why
Why we are building this
Three facts that do not go away.
Plants run blind on the attributes that matter
Fixed recipes, batch records and spot QC lab testing find drift after the batch is made: rejects, deviations, reprocessing, recalls, patient risk.
The craft is leaving
A severe, retiring formulation and process-engineering workforce caps rate and release under a mountain of GMP paperwork.
Principles
How we build
From the roadmap's guiding principles, and from the way regulated plants actually work.
Trust before autonomy
Validation, grounding, audit, human-in-the-loop and graduated control. There is no unattended level.
Compounding data moat, tenant by tenant
Every supervised correction trains the system, inside the tenant that made it.
Land narrow, expand relentlessly
One wedge workflow on one line, then modules, lines and sites, each expansion gated by validation and ROI review.
Say what is a target
Latencies, accuracies and corpus sizes are called targets until a design partner's own data measures them.
Quality outranks rate
In every arbitration a quality attribute wins over yield, energy or takt.
QA releases
Pildeon assembles evidence. A named human signs.
Run timeline · scenario
What we are actually building
Not a dashboard. A run engine that produces this record on every batch, on every line that licenses it.
run_b2c7e1
Line 2 · rotary tablet press · scenario
SUCCEEDED
-
01
ingest.batch_record
SUCCEEDED
1.2 s
Plant Orchestrator · Pulled the master batch record, the approved design-space limits for this formulation and tooling family, and the site autonomy policy from MES; locked the target envelope for the run.
-
02
twin.rehearse
SUCCEEDED
41 s
Plant Orchestrator · Twindra simulated 36 candidate setpoint vectors on the as-made batch twin (granulation DEM, compression and ejection risk, coating CFD, dissolution surrogate) and ranked them on predicted content uniformity, capping risk and takt.
-
03
blend.uniformity
SUCCEEDED
6 m 10 s
Blend-and-Dispense · Spectryn scored in-line NIR spectra against the formulation's chemometric model; the blend reached its uniformity end point with confidence bounds inside the site acceptance limit and blending stopped on evidence rather than on a fixed time.
-
04
granulate.dry
SUCCEEDED
3 m 48 s
Granulate-and-Dry · Inlet air temperature and drying airflow trimmed inside the approved window to bring loss-on-drying to the target moisture band for compression; the move was bounded, logged and inside the design space.
-
05
compress.press
SUCCEEDED
2 m 02 s
Compress-and-Fill · Main compression force and feed-frame speed adjusted inside the approved window to hold tablet weight and hardness on target while the twin's capping-risk estimate stayed under the site threshold.
-
06
coat.spray
SUCCEEDED
4 m 25 s
Coat-and-Dry · Spray rate and inlet temperature re-phased against bed temperature and exhaust humidity to hold the film-coat window and avoid twinning and mottling; no excursion from the validated recipe envelope.
-
07
inspect.tablets
SUCCEEDED
continuous
Defect-and-Inspect · Visqa classified chips, cracks, capping, spots, mottling and print defects on six synchronised cameras, within the sub-100 ms design budget, and linked a rising chip rate to coating spray rather than to tooling.
-
08
spectra.release_evidence
SUCCEEDED
38 s
Quality-and-Potency · Spectryn assembled the method-linked evidence chain for content uniformity and moisture with confidence bounds and citations to the validated analytical method, ready for QA review.
-
09
approve.qa
APPROVAL
3 m 14 s
Plant Orchestrator · Batch release is above every autonomy level Pildeon offers. The package was held for the named QA reviewer, who approved it in the review console; the decision, the reviewer identity and the timestamp are in the Part 11 audit trail.
-
10
release.genealogy
SUCCEEDED
52 s
Quality-and-Conformance · Conforma wrote the time-aligned batch genealogy (every sensor state, recommendation, approved action, equipment response and QC result) and the cited release package to the immutable audit trail.
Focus
What kind of company this is
Stated so there is no ambiguity for partners, programmes or investors.
Pildeon is
- An independent, pre-launch startup building original physical-AI software for oral solid dose manufacturing
- A product company: recurring software licensed per line, per plant and per group
- Built on accelerated computing because line-speed, safety-critical decisions cannot wait on the cloud or the lab
Pildeon is not
- A consultancy, an outsourced development shop or a systems integrator
- A reseller or distributor of anyone else's hardware or software
- A cloud provider, a crypto project or a division of another company
Accelerated computing
Physical AI, at the press
Tablets leave a rotary press by the hundreds of thousands an hour. Perception has to be local, deterministic and fast, so Pildeon runs GPU inference on the plant edge and keeps training, simulation and optimisation on DGX, HGX or OVX, on-prem where the data cannot leave the plant.
Edge perception
Multi-camera chip, crack, spot and print inspection and NIR and PAT fusion on the plant edge. Design targets: under 100 ms per camera frame group, under 500 ms for a fused risk score.
Validated model serving
Vision, spectral, time-series and process-reasoning models behind one orchestrator, versioned, tenant-isolated, with bounded actions and audit schemas enforced at the serving layer.
Training and fine-tuning
Defect vision, coating appearance, NIR and PAT chemometrics, press and coater time-series models and process-window models, trained under GxP change control.
As-made batch twin
GPU-accelerated DEM granulation, CFD coating spray and drying, compression and ejection risk and a dissolution surrogate. Design target: nightly design-space sweeps per formulation family.
Synthetic rare faults
Capping, lamination, sticking, mottling, segregation and print-defect scenarios generated for class balance, always labelled synthetic and evaluated apart from real GMP evidence.
Optimisation and handling
Campaign and changeover sequencing, drying and coating energy allocation and line balancing with cuOpt; sim-first IBC and tooling handling policies trained and rehearsed with Isaac.
Market
The market
From the market analysis. Figures are market estimates, not company results.
$18BOSD manufacturing automation, PAT and vision inspection, continuous-manufacturing control and pharma MES, growing about 13% a year
$4.6BServiceable: autonomous compression and coating control, content-uniformity and defect sensing, batch twins
$270MObtainable in three years by land-and-expand across lines, plants and sites
Tailwinds: the regulator-endorsed shift to continuous manufacturing and real-time release, generic and biosimilar volume, reshoring and supply security, and the retiring workforce.
Team
Who is building it
A small founding team, led by co-founders Mason Bennett (CEO) and Caleb Foster (CTO). Backgrounds, headquarters and incorporation details will be published here when confirmed; nothing about the team is invented on this site.
Mason Bennett
Mason owns the design-partner relationships, the wedge selection and the validation conversation with site directors, MSAT and QA.
Caleb Foster
Caleb owns the orchestrator, the policy engine, the audit architecture, the edge runtime and the model registry.
Perception, spectra, simulation, deployment
The roles on the careers page: the camera pipeline, the chemometrics, the twin's physics and the site deployments.
Writing
Recent notes
What we publish when we learn something worth publishing.
The formulator who adjusts the press by ear
A senior formulator hears the press change pitch, trims the force, saves the batch. That knowledge is real, it is valuable, and it is retiring faster than plants can replace it. Pildeon exists to capture it as supervised corrections and give it back to every line.
Why the blend should stop on spectra, not on the clock
A fixed blend time is a guess that was validated once. In-line NIR scored against a formulation-specific model lets the blender stop when uniformity is reached with confidence, and lets the same spectra become release evidence.
There is no unattended level, and that is the point
Pharma autonomy is graduated and bounded or it is not acceptable. Shadow, assist, supervised, bounded. Batch release stays with QA at every level, because the regulator asks who signed.
The first meeting
What each stakeholder asks first
Pildeon has no customer quotes to show yet, and will not invent any. These are the questions the three buyers in an OSD plant ask in the first meeting, and the answer each gets.
"What does this do to my reject rate, my deviation count and my release time, and how will you prove it on my line rather than on a slide?"
Site or manufacturing director · economic buyerAnswer: shadow mode first, baseline captured before any autonomous action, a written ROI target before a paid pilot.
"Will it ever move a setpoint outside the design space we validated, and can I see why it recommended every move it made?"
Formulation or process engineer (MSAT) · championAnswer: no, by construction. Every recommendation carries its reasoning trace and its citation.
"Where is the Part 11 audit trail, who signs the release, and what happens to my validated state when the model changes?"
QA, quality and compliance lead · approverAnswer: an immutable audit spine, a named QA reviewer on every release, and every model change under GxP change control.
Guardrails
An agent that can move a compression force needs a leash
Pildeon writes to production equipment in a GMP plant. Every capability is scoped to the approved design space, every write is policy-checked, every action is written to an immutable Part 11 audit trail the site owns, and no agent can release a batch.
- Bounded action space. Each agent can only write to an explicit setpoint allow-list, inside the limits the site's validation approved.
- Policy engine before every write. Autonomy level, design-space limits, batch state, model version and reviewer assignment are all evaluated before a setpoint moves.
- Human-in-the-loop gates. Batch release, any move outside the design space and any change to a validated parameter wait for a named QA reviewer.
- Immutable audit trail. Append-only, hash-chained, exportable, retained on the site's own storage, with reviewer identity and timestamp on every decision.
- Hard fallback. Loss of the edge node, the network or the model returns the line to the equipment's last known-good recipe.
- Tenant and IP isolation. Formulations, recipes and models never cross a customer boundary. Validated on-prem deployment is available for regulated producers.
Compliance posture
| Standard | Scope | Status |
|---|---|---|
| 21 CFR Part 11 | Audit trail, e-signatures, records | RUNNING Designed in from day one |
| GAMP 5 | Validation package for the platform | RUNNING In progress, planned for the first design partners |
| cGMP · ICH Q8 to Q13 | Design space, QbD, continuous manufacturing | RUNNING Design-aligned; site validation decides |
| SOC 2 Type I | Cloud control plane | QUEUED Planned, first six months |
| SOC 2 Type II | Cloud control plane | QUEUED Planned, months six to twelve |
| Data residency | Validated on-prem, air-gapped option | SUCCEEDED Available by design |
FAQ
Straight answers
The questions site directors, MSAT engineers and QA leads actually ask in the first meeting.
Yes, but only inside an explicit setpoint allow-list bounded by the design space your validation approved, and only at the autonomy level your site has set. Level 0 is shadow mode: Pildeon observes and predicts and writes nothing. Most sites spend their first weeks there.
No. The approved design space is a wall the policy engine enforces at call time. A move outside it, or a change to a validated parameter, is a change-control event that waits for QA sign-off. No autonomy level removes that gate.
A named QA reviewer, every time. Pildeon assembles the evidence chain and the cited release package; the reviewer approves or rejects it in the review console, and the decision, identity and timestamp land in the Part 11 audit trail.
The line returns to the equipment's own last known-good recipe. Pildeon is a supervisory layer on top of your existing control systems, never a replacement, so an outage degrades the line to the way it runs today, not to a stop.
Only if you choose cloud training. Formulations, recipes, spectra and defect libraries are tenant-isolated and never used to train another customer's models. Validated on-prem deployment with an air-gapped plant edge is available.
Shadow mode on one wedge workflow first, with baseline rejects, deviations, yield, energy and release time captured before any autonomous action. Assist mode once prediction accuracy is shown against QC results. A paid validated pilot only when there is a written ROI target. Timelines depend on the site's validation and change-control calendar.
Get started
Come build the tablet plant's operating system
As a design partner, a partner or an engineer. Shadow mode is where every conversation starts.