Short essays on tablet making, spectra, inspection and what autonomy has to look like to be acceptable in a GMP plant. Written by the team, grounded in the documents we build from, and free of customer claims we cannot make yet.
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.
Newest first.
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.
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.
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.
Offline DoE models one step. A twin of the formulation and tooling family simulates granulation, compression, coating and dissolution together, so the setpoint vector is rehearsed before a tablet is pressed and the design space is defended with physics.
No single site collects enough one-in-a-million defects to train a robust model. A cross-plant corpus plus synthetic rare faults, labelled synthetic and kept apart from GMP evidence, is how inspection stops over-rejecting good tablets.
The data that proves a batch was made right is scattered across historians, LIMS and PDFs. A time-aligned genealogy and a cited release package turn release from a paper hunt into a review.
When a note mentions step 3 or step 9, it means this scenario run.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
Every tool invocation, argument and result is written to an immutable, human-readable log, and every reasoning step is expandable. Nothing about a run is hidden from the plant or from QA.
Plan, thought, action, observation, exactly as the orchestrator records it.
Run one immediate-release tablet batch through granulation, compression, coating and inspection inside the approved design space, with QA approval before release.
Rehearse on the twin first. Stop blending on NIR evidence rather than on a fixed time. Trim drying, compression and coating only inside the approved design space. Inspect continuously. Hold release for the named QA reviewer, always.
The fixed recipe blends for a set time regardless of what the spectra say. On the twin, the candidate that stops on evidence and trims inlet temperature before compression keeps content uniformity and moisture inside their limits with the lowest predicted capping risk.
twin.simulate(candidates=36) → candidate #14: evidence-based blend end point, bounded drying trim, compression force held inside the window, spray rate re-phased to bed temperature.
Every candidate that pushed turret speed for takt raised predicted capping risk above the site threshold and was discarded. Rate is never traded for a quality attribute.
Execute candidate #14 under autonomy level L2: five setpoint moves inside the design space, each logged. Batch release routed to QA.
Chip rate rose on camera 4 at 06:27:10. Visqa attributed it to coating spray rather than tooling; a bounded spray-rate trim returned it to baseline in about two minutes.
Scenario complete. Every move inside the approved design space, the QA approval recorded with identity and timestamp, and the cited release package written by Conforma to the immutable audit trail.
Each series is a sequence of notes on one theme.
Model cards, golden datasets, change control and drift: how a model version becomes a GxP record and stays one.
Content uniformity, moisture, hardness, film, dissolution: what each needs sensed, modelled and bounded.
What the site director, the MSAT engineer and the QA lead each need to see before they say yes, and why all three must.
Our beat, stated.
A tablet plant does not go from fixed recipes to autonomy in one step, and validated parameters never change without sign-off. Pildeon makes the level explicit, auditable and reversible at any time.
| Level | What the agent does | What the human does | Typical time to reach |
|---|---|---|---|
| L0 · Shadow | Observes, scores and predicts; writes nothing | Runs the line as today; compares predictions to QC results | Weeks 1 to 6 of a design partnership |
| L1 · Assist | Recommends setpoint moves and explains why | Process engineer enters the move; QA reviews the log | After shadow-mode accuracy is shown |
| L2 · Supervised | Proposes a bounded move; it executes on approval | Approves each move in the review console | After assist-mode ROI is shown |
| L3 · Bounded | Moves low-risk compression, coating and inspection setpoints inside the approved design space | Handles exceptions; approves every release | After validation and change-control review |
There is no unattended level. Batch release and any move outside the approved design space always wait for a named QA reviewer, and every model or prompt change runs under GxP change control.
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.
When a note cites a latency or a corpus size, it is one of these design targets, and it is called a target.
Training corpus targets across design partners: 10M+ tablet and coating images, 50k+ NIR and PAT spectra, 100k+ process time-series windows, 5k+ labelled deviation investigations. Targets, not holdings.
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.
| 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 |
Pildeon reads and writes through the systems already on the floor: presses, coaters, granulators, PAT probes, MES, LIMS and historians. No rip-and-replace, no parallel historian. Connectors are built with design partners against their stacks; the vendors listed are the ones common in OSD plants.
GEA, Glatt, Syntegon, Freund-Vector, L.B. Bohle
Blender, granulator and fluid-bed telemetry; bounded setpoint writes
Fette Compacting, Korsch, IMA, Syntegon, MG2
Force curves, fill depth, ejection force; bounded setpoint writes
GEA, Glatt, O'Hara, Thomas, Freund
Spray, inlet, bed temperature, exhaust humidity; bounded writes
Bruker, Sartorius, Viavi probes and analysers
Spectra across blend, granulation, drying and compression
Line cameras and existing inspection systems
Frames, defect maps, reviewed images
Körber Werum PAS-X, Rockwell, Siemens Opcenter
Master batch records, campaigns, batch genealogy
Site LIMS, OSIsoft PI and equivalent historians
QC results, time-series backfill and replay
Azure AD, Okta, LDAP · NVIDIA Jetson and on-prem GPU
SSO, RBAC, named approvers · inference at the line
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.
An email when a new note is published. Nothing else.
↑↓ navigate↵ openesc close
