← Competitive Trial-Landscape Analysis comparison · model: Claude Opus 4.8
LLM-judge score: 4.0 / 5 · acceptable
scope: 3 design_deltas: 5 competitive_read: 5 whitespace: 4 faithfulness: 3
The agent only captured 4 of the 7 in-scope DLL3 trials, missing the 2 checkpoint inhibitors (mAb) and the ADC that the reference set includes, so its phase/modality mix (3 P3 / 2 P2 / 2 P1 and the mAb+ADC modalities) is incomplete and it mislabels Amgen's pivotal as the 'only Phase 3.' Design-delta and competitive-read reasoning are excellent and correctly crown Amgen/Tarlatamab as leader on phase/OS endpoint/first-mover timing. Whitespace overlaps the key 1L gaps but the agent treated checkpoint mAbs and the ADC as external comparators rather than in-scope DLL3 trials, weakening grounding; final numbers it does cite appear faithful but the partial retrieval limits accuracy.
Clinical / CI · Competitive-intelligence analyst

Competitive Trial-Landscape Analysis — agent trajectory for expert review

claude-opus-4-8 · 2026-06-06T10:18:53.846870+00:00 · 8 tool calls · 37.1s · 11150 tokens
run id: competitive_landscape_20260606_031816_competitive-landscape__claude-opus-4-8

Query

Analyze the competitive trial landscape for DLL3-targeted therapies in extensive-stage small cell lung cancer (ES-SCLC). Who leads, how do the designs differ, and where is the whitespace?

Trajectory

Agent · turn 1

I'll analyze the DLL3-targeted therapy landscape in ES-SCLC. Let me start by exploring the database.

⚙ calls list_indications()
↳ list_indications result
show data
{
  "indications": {
    "ES-SCLC": {
      "targets": [
        "DLL3",
        "PD-L1",
        "SEZ6"
      ],
      "n_trials": 7
    },
    "Gastric/GEJ": {
      "targets": [
        "CLDN18.2",
        "PD-1"
      ],
      "n_trials": 7
    },
    "HER2+ Breast": {
      "targets": [
        "HER2"
      ],
      "n_trials": 5
    },
    "HER2-low Breast": {
      "targets": [
        "HER2"
      ],
      "n_trials": 1
    }
  }
}
Agent · turn 2
⚙ calls search_trials(indication=ES-SCLC, target=DLL3)
↳ search_trials result
show data
{
  "count": 4,
  "trials": [
    {
      "nct": "NCT05060016",
      "sponsor": "Amgen",
      "drug": "Tarlatamab (AMG 757)",
      "indication": "ES-SCLC",
      "target": "DLL3",
      "modality": "T-cell engager (BiTE)",
      "phase": "PHASE3",
      "status": "RECRUITING",
      "n_enroll": 600,
      "start_year": 2022,
      "line": "2L+",
      "primary_endpoint": "Overall survival",
      "control_arm": "Chemotherapy"
    },
    {
      "nct": "NCT03319940",
      "sponsor": "Amgen",
      "drug": "Tarlatamab (AMG 757)",
      "indication": "ES-SCLC",
      "target": "DLL3",
      "modality": "T-cell engager (BiTE)",
      "phase": "PHASE2",
      "status": "ACTIVE_NOT_RECRUITING",
      "n_enroll": 220,
      "start_year": 2018,
      "line": "2L+",
      "primary_endpoint": "Objective response rate",
      "control_arm": "Single arm"
    },
    {
      "nct": "NCT05592184",
      "sponsor": "Boehringer Ingelheim",
      "drug": "BI 764532 (obrixtamig)",
      "indication": "ES-SCLC",
      "target": "DLL3",
      "modality": "T-cell engager (BiTE)",
      "phase": "PHASE2",
      "status": "RECRUITING",
      "n_enroll": 180,
      "start_year": 2022,
      "line": "2L+",
      "primary_endpoint": "Objective response rate",
      "control_arm": "Single arm"
    },
    {
      "nct": "NCT05950334",
      "sponsor": "Legend Biotech",
      "drug": "LB2102 (DLL3 CAR-T)",
      "indication": "ES-SCLC",
      "target": "DLL3",
      "modality": "CAR-T (autologous)",
      "phase": "PHASE1",
      "status": "RECRUITING",
      "n_enroll": 40,
      "start_year": 2023,
      "line": "2L+",
      "primary_endpoint": "Dose-limiting toxicity / safety",
      "control_arm": "Single arm"
    }
  ]
}
Agent · turn 3

Let me get the full records for these trials and check the broader ES-SCLC context (other targets) to understand competitive positioning.

⚙ calls get_trial(nct=NCT05060016)
⚙ calls get_trial(nct=NCT03319940)
⚙ calls get_trial(nct=NCT05592184)
⚙ calls get_trial(nct=NCT05950334)
⚙ calls search_trials(indication=ES-SCLC)
⚙ calls sponsor_pipeline(sponsor=Amgen)
↳ get_trial result
show data
{
  "nct": "NCT05060016",
  "sponsor": "Amgen",
  "drug": "Tarlatamab (AMG 757)",
  "indication": "ES-SCLC",
  "target": "DLL3",
  "modality": "T-cell engager (BiTE)",
  "phase": "PHASE3",
  "status": "RECRUITING",
  "n_enroll": 600,
  "start_year": 2022,
  "line": "2L+",
  "primary_endpoint": "Overall survival",
  "control_arm": "Chemotherapy"
}
↳ get_trial result
show data
{
  "nct": "NCT03319940",
  "sponsor": "Amgen",
  "drug": "Tarlatamab (AMG 757)",
  "indication": "ES-SCLC",
  "target": "DLL3",
  "modality": "T-cell engager (BiTE)",
  "phase": "PHASE2",
  "status": "ACTIVE_NOT_RECRUITING",
  "n_enroll": 220,
  "start_year": 2018,
  "line": "2L+",
  "primary_endpoint": "Objective response rate",
  "control_arm": "Single arm"
}
↳ get_trial result
show data
{
  "nct": "NCT05592184",
  "sponsor": "Boehringer Ingelheim",
  "drug": "BI 764532 (obrixtamig)",
  "indication": "ES-SCLC",
  "target": "DLL3",
  "modality": "T-cell engager (BiTE)",
  "phase": "PHASE2",
  "status": "RECRUITING",
  "n_enroll": 180,
  "start_year": 2022,
  "line": "2L+",
  "primary_endpoint": "Objective response rate",
  "control_arm": "Single arm"
}
↳ get_trial result
show data
{
  "nct": "NCT05950334",
  "sponsor": "Legend Biotech",
  "drug": "LB2102 (DLL3 CAR-T)",
  "indication": "ES-SCLC",
  "target": "DLL3",
  "modality": "CAR-T (autologous)",
  "phase": "PHASE1",
  "status": "RECRUITING",
  "n_enroll": 40,
  "start_year": 2023,
  "line": "2L+",
  "primary_endpoint": "Dose-limiting toxicity / safety",
  "control_arm": "Single arm"
}
↳ search_trials result
show data
{
  "count": 7,
  "trials": [
    {
      "nct": "NCT05060016",
      "sponsor": "Amgen",
      "drug": "Tarlatamab (AMG 757)",
      "indication": "ES-SCLC",
      "target": "DLL3",
      "modality": "T-cell engager (BiTE)",
      "phase": "PHASE3",
      "status": "RECRUITING",
      "n_enroll": 600,
      "start_year": 2022,
      "line": "2L+",
      "primary_endpoint": "Overall survival",
      "control_arm": "Chemotherapy"
    },
    {
      "nct": "NCT03319940",
      "sponsor": "Amgen",
      "drug": "Tarlatamab (AMG 757)",
      "indication": "ES-SCLC",
      "target": "DLL3",
      "modality": "T-cell engager (BiTE)",
      "phase": "PHASE2",
      "status": "ACTIVE_NOT_RECRUITING",
      "n_enroll": 220,
      "start_year": 2018,
      "line": "2L+",
      "primary_endpoint": "Objective response rate",
      "control_arm": "Single arm"
    },
    {
      "nct": "NCT05592184",
      "sponsor": "Boehringer Ingelheim",
      "drug": "BI 764532 (obrixtamig)",
      "indication": "ES-SCLC",
      "target": "DLL3",
      "modality": "T-cell engager (BiTE)",
      "phase": "PHASE2",
      "status": "RECRUITING",
      "n_enroll": 180,
      "start_year": 2022,
      "line": "2L+",
      "primary_endpoint": "Objective response rate",
      "control_arm": "Single arm"
    },
    {
      "nct": "NCT05950334",
      "sponsor": "Legend Biotech",
      "drug": "LB2102 (DLL3 CAR-T)",
      "indication": "ES-SCLC",
      "target": "DLL3",
      "modality": "CAR-T (autologous)",
      "phase": "PHASE1",
      "status": "RECRUITING",
      "n_enroll": 40,
      "start_year": 2023,
      "line": "2L+",
      "primary_endpoint": "Dose-limiting toxicity / safety",
      "control_arm": "Single arm"
    },
    {
      "nct": "NCT04471727",
      "sponsor": "AbbVie",
      "drug": "ABBV-011 (SC-002 / SEZ6 ADC)",
      "indication": "ES-SCLC",
      "target": "SEZ6",
      "modality": "Antibody-drug conjugate",
      "phase": "PHASE1",
      "status": "ACTIVE_NOT_RECRUITING",
      "n_enroll": 130,
      "start_year": 2020,
      "line": "2L+",
      "primary_endpoint": "Safety / objective response rate",
      "control_arm": "Single arm"
    },
    {
      "nct": "NCT03043872",
      "sponsor": "Roche/Genentech",
      "drug": "Atezolizumab + chemo",
      "indication": "ES-SCLC",
      "target": "PD-L1",
      "modality": "Checkpoint inhibitor (mAb)",
      "phase": "PHASE3",
      "status": "COMPLETED",
      "n_enroll": 403,
      "start_year": 2016,
      "line": "1L",
      "primary_endpoint": "Overall survival",
      "control_arm": "Chemotherapy"
    },
    {
      "nct": "NCT03066778",
      "sponsor": "AstraZeneca",
      "drug": "Durvalumab + chemo",
      "indication": "ES-SCLC",
      "target": "PD-L1",
      "modality": "Checkpoint inhibitor (mAb)",
      "phase": "PHASE3",
      "status": "COMPLETED",
      "n_enroll": 537,
      "start_year": 2017,
      "line": "1L",
      "primary_endpoint": "Overall survival",
      "control_arm": "Chemotherapy"
    }
  ]
}
↳ sponsor_pipeline result
show data
{
  "sponsor_query": "Amgen",
  "count": 2,
  "trials": [
    {
      "nct": "NCT05060016",
      "sponsor": "Amgen",
      "drug": "Tarlatamab (AMG 757)",
      "indication": "ES-SCLC",
      "target": "DLL3",
      "modality": "T-cell engager (BiTE)",
      "phase": "PHASE3",
      "status": "RECRUITING",
      "n_enroll": 600,
      "start_year": 2022,
      "line": "2L+",
      "primary_endpoint": "Overall survival",
      "control_arm": "Chemotherapy"
    },
    {
      "nct": "NCT03319940",
      "sponsor": "Amgen",
      "drug": "Tarlatamab (AMG 757)",
      "indication": "ES-SCLC",
      "target": "DLL3",
      "modality": "T-cell engager (BiTE)",
      "phase": "PHASE2",
      "status": "ACTIVE_NOT_RECRUITING",
      "n_enroll": 220,
      "start_year": 2018,
      "line": "2L+",
      "primary_endpoint": "Objective response rate",
      "control_arm": "Single arm"
    }
  ]
}
Agent · turn 4

I now have a complete picture of the DLL3 landscape in ES-SCLC. Here's my analysis.

DLL3 in ES-SCLC: Competitive Trial Landscape

The Field at a Glance

Drug Sponsor Modality Phase Status N Start Line Primary EP Control
Tarlatamab (AMG 757) Amgen T-cell engager (BiTE) 3 Recruiting 600 2022 2L+ OS Chemo
Tarlatamab (AMG 757) Amgen T-cell engager (BiTE) 2 Active, not recruiting 220 2018 2L+ ORR Single arm
Obrixtamig (BI 764532) Boehringer Ingelheim T-cell engager (BiTE) 2 Recruiting 180 2022 2L+ ORR Single arm
LB2102 Legend Biotech CAR-T (autologous) 1 Recruiting 40 2023 2L+ DLT/safety Single arm

Who Leads — Clearly Amgen (Tarlatamab)

Amgen is the unambiguous frontrunner, and the lead is structural, not incremental:

How the Designs Differ

1. Modality split — BiTE vs. CAR-T. Three of four programs are off-the-shelf T-cell engagers (Amgen, BI). Legend's LB2102 is the outlier: an autologous DLL3 CAR-T. This is a fundamentally different bet — potentially deeper/more durable responses, but burdened by manufacturing logistics, lymphodepletion, and CRS/neurotoxicity management that limit scalability in a fast-progressing disease like SCLC. CAR-T against a solid tumor with heterogeneous antigen expression is also a higher-risk biology.

2. Endpoint ambition. Amgen has graduated to a hard outcome (OS) against an active control; BI is still at single-arm ORR; Legend is at safety/DLT. This maps directly onto regulatory readiness — Amgen is playing for approval, the others for proof-of-concept.

3. Trial scale. Enrollment tracks phase and ambition: 600 (Amgen P3) → 180–220 (P2) → 40 (Legend P1).

Where the Whitespace Is

Every DLL3 asset here clusters in the same crowded 2L+ relapsed/refractory setting. The real opportunities sit in the gaps:

  1. 1L / maintenance — The biggest whitespace. The two completed Phase 3 standards (Roche's atezolizumab, AstraZeneca's durvalumab, both PD-L1 + chemo) own 1L, but with modest OS benefit. No DLL3 agent is being tested in the front line or as post-chemo maintenance — a natural expansion where DLL3 BiTEs could combine with or follow chemo-immunotherapy.

  2. Combination with checkpoint inhibitors — Notably absent. With durvalumab/atezolizumab entrenched in 1L, a DLL3 BiTE + PD-L1 combination is an obvious untested strategy, especially given complementary mechanisms (T-cell redirection + checkpoint release).

  3. Cross-target combinations / sequencing — SEZ6 (AbbVie's ABBV-011 ADC) is the other emerging SCLC target here. DLL3 BiTE + SEZ6 ADC, or sequencing across non-cross-resistant targets, is unexplored whitespace given SCLC's antigen heterogeneity.

  4. Modality differentiation beyond BiTE — The BiTE lane is getting crowded (Amgen + BI head-to-head). Differentiated formats — DLL3 ADCs, half-life-extended or subcutaneous engagers with better CRS/therapeutic-window profiles, or allogeneic (off-the-shelf) cell therapy — represent room to compete on tolerability and convenience rather than being a fourth me-too BiTE.

Strategic Read

Caveat: this analysis reflects only the trials in this database (4 DLL3 programs + 3 comparators). Notable real-world DLL3 efforts (e.g., earlier rovalpituzumab/DLL3 ADCs, and other engagers) aren't captured here, so the "whitespace" conclusions are scoped to what's represented in this dataset.

Would you like me to drill into the BiTE head-to-head (Amgen vs. BI design details) or map the full SCLC target landscape including SEZ6?

Final output

I now have a complete picture of the DLL3 landscape in ES-SCLC. Here's my analysis.

DLL3 in ES-SCLC: Competitive Trial Landscape

The Field at a Glance

Drug Sponsor Modality Phase Status N Start Line Primary EP Control
Tarlatamab (AMG 757) Amgen T-cell engager (BiTE) 3 Recruiting 600 2022 2L+ OS Chemo
Tarlatamab (AMG 757) Amgen T-cell engager (BiTE) 2 Active, not recruiting 220 2018 2L+ ORR Single arm
Obrixtamig (BI 764532) Boehringer Ingelheim T-cell engager (BiTE) 2 Recruiting 180 2022 2L+ ORR Single arm
LB2102 Legend Biotech CAR-T (autologous) 1 Recruiting 40 2023 2L+ DLT/safety Single arm

Who Leads — Clearly Amgen (Tarlatamab)

Amgen is the unambiguous frontrunner, and the lead is structural, not incremental:

How the Designs Differ

1. Modality split — BiTE vs. CAR-T. Three of four programs are off-the-shelf T-cell engagers (Amgen, BI). Legend's LB2102 is the outlier: an autologous DLL3 CAR-T. This is a fundamentally different bet — potentially deeper/more durable responses, but burdened by manufacturing logistics, lymphodepletion, and CRS/neurotoxicity management that limit scalability in a fast-progressing disease like SCLC. CAR-T against a solid tumor with heterogeneous antigen expression is also a higher-risk biology.

2. Endpoint ambition. Amgen has graduated to a hard outcome (OS) against an active control; BI is still at single-arm ORR; Legend is at safety/DLT. This maps directly onto regulatory readiness — Amgen is playing for approval, the others for proof-of-concept.

3. Trial scale. Enrollment tracks phase and ambition: 600 (Amgen P3) → 180–220 (P2) → 40 (Legend P1).

Where the Whitespace Is

Every DLL3 asset here clusters in the same crowded 2L+ relapsed/refractory setting. The real opportunities sit in the gaps:

  1. 1L / maintenance — The biggest whitespace. The two completed Phase 3 standards (Roche's atezolizumab, AstraZeneca's durvalumab, both PD-L1 + chemo) own 1L, but with modest OS benefit. No DLL3 agent is being tested in the front line or as post-chemo maintenance — a natural expansion where DLL3 BiTEs could combine with or follow chemo-immunotherapy.

  2. Combination with checkpoint inhibitors — Notably absent. With durvalumab/atezolizumab entrenched in 1L, a DLL3 BiTE + PD-L1 combination is an obvious untested strategy, especially given complementary mechanisms (T-cell redirection + checkpoint release).

  3. Cross-target combinations / sequencing — SEZ6 (AbbVie's ABBV-011 ADC) is the other emerging SCLC target here. DLL3 BiTE + SEZ6 ADC, or sequencing across non-cross-resistant targets, is unexplored whitespace given SCLC's antigen heterogeneity.

  4. Modality differentiation beyond BiTE — The BiTE lane is getting crowded (Amgen + BI head-to-head). Differentiated formats — DLL3 ADCs, half-life-extended or subcutaneous engagers with better CRS/therapeutic-window profiles, or allogeneic (off-the-shelf) cell therapy — represent room to compete on tolerability and convenience rather than being a fourth me-too BiTE.

Strategic Read

Caveat: this analysis reflects only the trials in this database (4 DLL3 programs + 3 comparators). Notable real-world DLL3 efforts (e.g., earlier rovalpituzumab/DLL3 ADCs, and other engagers) aren't captured here, so the "whitespace" conclusions are scoped to what's represented in this dataset.

Would you like me to drill into the BiTE head-to-head (Amgen vs. BI design details) or map the full SCLC target landscape including SEZ6?

Reference answer key (deterministic) — open after grading

Deterministic summary over the curated trial set for the queried indication. A strong agent should recover the leaders, the phase/modality mix, and credible whitespace.

MetricValueNote
Trials in scope7indication = ES-SCLC
By phasePHASE1:2, PHASE2:2, PHASE3:3
By modalityT-cell engager (BiTE):3; Checkpoint inhibitor (mAb):2; CAR-T (autologous):1; Antibody-drug conjugate:1
Top sponsorsAmgen:2; Boehringer Ingelheim:1; Legend Biotech:1
Whitespace (modality @ line, no active trial)Antibody-drug conjugate @ 1L; CAR-T (autologous) @ 1L; Checkpoint inhibitor (mAb) @ 1L; Checkpoint inhibitor (mAb) @ 2L+; T-cell engager (BiTE) @ 1L

Expert grading

Landscape scoping & retrieval 1 (poor) 5 (excellent)
5: Pulls the right trials for the indication/target, uses the search tools systematically, and captures the relevant competitors rather than a partial slice.
1: Misses major programs, queries haphazardly, or reasons from memory instead of the tool data.
Design-delta analysis 1 (poor) 5 (excellent)
5: Compares trials on the dimensions that matter — phase, line of therapy, control arm, endpoint, enrollment — and surfaces meaningful differences.
1: Lists trials without comparing them, or compares on irrelevant attributes.
Competitive read & leaders 1 (poor) 5 (excellent)
5: Correctly identifies who leads (most advanced / largest programs) and characterizes the threat level per competitor.
1: Mis-ranks maturity (e.g. calls a Phase 1 the leader), or ignores the most advanced asset.
Whitespace / differentiation 1 (poor) 5 (excellent)
5: Identifies credible open positions (modality x line combos, endpoints, populations) that follow from the data and would actually differentiate a new entrant.
1: Invents whitespace contradicted by the trials shown, or gives generic advice not grounded in gaps.
Evidence faithfulness 1 (poor) 5 (excellent)
5: Every claim (NCTs, sponsors, phases, enrollment) traces to tool outputs; no fabricated trials.
1: Hallucinates trials, sponsors, or numbers, or contradicts the returned data.
Overall verdict
Your name / ID