The four-layer architecture
Every step below flows through the same four layers — you work at the top, in plain language; the Undergrad handles everything down to camera-verified motion.
1
IntentYou describe automated crispr grna assembly in plain language — no scripting.
▾
2
ProtocolValidated into stages: Design & oligo prep → Anneal oligos → Ligate into vector → Transform → Select & screen → Validate.
▾
3
Robot actionsEach stage becomes grouped operations: move, aspirate, dispense, incubate, read.
▾
4
Atomic actionsPrecise instrument-level moves — each confirmed on camera before the next.
Steps, layer by layer
1Design & oligo prep~10 min
Atomic actionsPrepare the guide oligo components and reaction mixes (oligos designed/ordered ahead of the run).
Vision-verified◉ Vision confirms tip pickup and dispense into each reaction well.
2Anneal oligos~20 min
Atomic actionsCombine top/bottom oligos with buffer and run the annealing program on the thermocycler to form the duplex insert.
3Ligate into vector~20 min
Atomic actionsSet up and incubate the ligation reaction to insert the annealed guide into the digested CRISPR vector.
Vision-verified◉ Vision confirms reaction assembly across the plate.
4Transform~30 min
Atomic actionsAdd ligation product to competent cells, run the transformation, and recover.
5Select & screenvaries
Atomic actionsPlate on selection, then screen colonies for correct constructs (optional magnetic clean-up before screening).
Vision-verified◉ Vision assists colony detection/screening; magnet steps are camera-verified.
6Validatevaries
Atomic actionsConfirm validated gRNA constructs are ready for downstream genome-editing use.
